© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-3-27B-IT · 31-GEMMASCOPE-2-RES-65K · 2776 ｜ Neuronpedia

Home
Gemma-3-27B-IT
31-GEMMASCOPE-2-RES-65K
2776

INDEX

Explanations

for clarity or ease

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

を通して

0.40

謖

0.40

 Almost

0.38

 sorghum

0.37

Almost

0.36

derive

0.36

 Shivaji

0.36

almost

0.35

自带

0.35

有很多

0.35

POSITIVE LOGITS

 avoid

0.89

 tránh

0.86

避免

0.81

 avoids

0.79

 éviter

0.77

 Avoid

0.74

Avoid

0.74

 menghindari

0.74

 avoiding

0.73

avoid

0.72

Activations Density 0.510%

No Known Activations