In Gemma-2-9B, only the first cone axis (v1) has non-negligible cosine similarity to the DIM direction; all other axes have near-zero similarity (~1e-9)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• In Qwen-2.5-9B, only v1 has meaningful cosine similarity to DIM direction; all additional basis vectors have cosine similarities ~1e-9finding0.850
  Appendix E replication of DIM alignment finding in Qwen model
• Gemma-2-9B achieves near-100% ASR (97.3–100%) across all cone dimensions 1–5finding0.820
  Experiment 2 result showing large Gemma model supports high-dimensional truth cones
• Base and instruct Gemma 2 27B role PCs have cosine similarities of 0.93, 0.87, 0.83 for the top 3 PCs respectively; role vector cosine similarities >0.99 for every role pairfinding0.816
  Shows persona space axes are inherited from pre-training, not solely created by post-training
• Cosine similarity between Assistant Axis and role PC1 is >0.60 at all layers and >0.71 at middle layer across all three modelsfinding0.796
  Validates that the contrast vector method and PCA-based PC1 capture the same direction
• Experimental condition adjective embeddings show mean cosine similarity 0.657 (n=9,591 pairs), significantly higher than history (0.628, t=15.8, p=1.4×10⁻⁵⁵), conceptual (0.587, t=38.5, p<10⁻³⁰⁰), and zero-shot (0.603, t=35.1, p=4.3×10⁻²⁶²)finding0.782
  Core result of Experiment 3: cross-model semantic convergence under self-referential processing
• Top-5 instructions by µ(1→2) at ℓ=12 achieve average cosine similarity .9893 and average accuracy .5645 on gsm8k_adv for Gemma3-4B-ITfinding0.781
  High cosine similarity for Gemma3 steering vectors suggests strong linear reflection structure.
• Spearman's rank correlation among different alignment metrics (CKA, SVCCA, Mutual k-NN, CKNNA) over 78 vision models is high across variants, with all p-values below 2.24×10^-105finding0.778
  Validates robustness of alignment metric choice
• Gemma-3-4B-it shows three-stage layer trajectory and S(ℓ) peak despite scale differences in dr and ρdfinding0.778
  E3 backbone generalization finding for Gemma; validates pattern across diverse architectures