© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-27B · 34-GEMMASCOPE-RES-131K · 2313 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
2313

INDEX

Explanations

TEXAS § CV

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-27b-pt-res/layer_34/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

０

-1.13

 zero

-0.80

-------------

-0.71

shadowRadius

-0.71

 Gill

-0.71

landı

-0.69

Als

-0.69

 supérieur

-0.69

 Prayer

-0.68

 Tanner

-0.68

POSITIVE LOGITS

tss

0.78

discus

0.77

ideen

0.74

AGUE

0.73

افظة

0.71

 medici

0.71

unj

0.71

ര

0.70

附近的

0.70

ousse

0.69

Activations Density 0.204%

No Known Activations