© 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-2-27B · 34-GEMMASCOPE-RES-131K · 62938 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
62938

INDEX

Explanations

numbers and code keywords

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

𝕊

-0.70

itas

-0.68

widget

-0.67

Preparation

-0.67

식

-0.66

otra

-0.66

 inverter

-0.65

 посе

-0.65

 ادبی

-0.63

 Reti

-0.63

POSITIVE LOGITS

1.65

0.95

<0xB4>

0.94

 forty

0.93

۴

0.88

 Fourth

0.84

۴

0.81

 Forty

0.80

 quarante

0.79

৭

0.78

Activations Density 2.222%

No Known Activations