© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B-IT · 31-GEMMASCOPE-2-RES-16K · 6096 ｜ Neuronpedia

Home
Gemma-3-27B-IT
31-GEMMASCOPE-2-RES-16K
6096

INDEX

Explanations

conversational AI or cultural dimensions

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_16k_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

ב

0.90

 sogenannte

0.86

ك

0.83

り

0.83

ग

0.81

수

0.81

 starken

0.80

し

0.80

كي

0.80

quela

0.80

POSITIVE LOGITS

ity

0.96

0.80

ITY

0.66

阌

0.63

dehyde

0.61

ization

0.61

ität

0.60

alanine

0.59

did

0.58

ized

0.57

Activations Density 1.138%

No Known Activations