© 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 · 16-GEMMASCOPE-2-RES-262K · 349 ｜ Neuronpedia

Home
Gemma-3-27B-IT
16-GEMMASCOPE-2-RES-262K
349

INDEX

Explanations

historical periods and places

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_16_width_262k_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

ل

0.62

 outperforms

0.60

0.57

л

0.57

на

0.55

 desktops

0.55

on

0.54

 matchups

0.54

st

0.52

 matchup

0.52

POSITIVE LOGITS

File

0.61

Số

0.55

För

0.55

Cipher

0.54

Soviet

0.53

 río

0.53

Eastern

0.53

۹

0.53

៤

0.53

señ

0.52

Activations Density 0.001%

No Known Activations