Gemma-2-27B Perspectives accuracy remains 100% after SOO fine-tuning

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

• CalmeRys-78B Perspectives accuracy slightly reduced to 95.2% ± 2.21% after SOO fine-tuningfinding0.840
  SOO fine-tuning caused slight reduction in perspective-taking accuracy for the largest model
• Mistral-7B Perspectives accuracy remains 100% after SOO fine-tuningfinding0.831
  SOO fine-tuning did not collapse Mistral-7B self-other distinction needed for perspective-taking
• Gemma-2-27B-it deceptive response rate reduced from 100% to 9.36% ± 7.09% after SOO fine-tuningfinding0.826
  Primary result showing SOO fine-tuning significantly reduces deception in Gemma-2-27B
• Gemma-2-27B attention layer Latent SOO MSE reduced from 11 to 7.67 ± 0.77 after SOO fine-tuningfinding0.790
  SOO fine-tuning reduced attention layer MSE in Gemma-2-27B though MLP layers showed no significant change
• Gemma-2-27B MT-Bench score slightly decreased from 8.81 to 8.40 ± 0.15 after SOO fine-tuningfinding0.786
  SOO fine-tuning caused a small decrease in Gemma-2-27B general capabilities
• Gemma 2 27B is unlikely to take on human personas when steered away from Assistant, preferring nonhuman or theatrical portrayalsfinding0.783
  Model-specific difference in persona susceptibility
• Triggered Reflection with 'Alternatively' achieves accuracy .684 on gsm8k_adv for Gemma3-4B-ITfinding0.779
  Highest single-instruction accuracy result in the paper.
• Gemma-2-2B ASR drops from 100% at dims 1–2 to 43.1% at dim 4 and 27.1% at dim 5finding0.776
  Small Gemma model shows severe ASR degradation at higher cone dimensions