© 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 · 62995 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
62995

INDEX

Explanations

let alone

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

 much

-2.06

much

-1.66

Much

-1.23

 Much

-1.23

只

-0.84

 mycket

-0.83

 MUCH

-0.83

膵

-0.83

และ

-0.81

 äldre

-0.80

POSITIVE LOGITS

 alone

1.39

alone

0.91

 along

0.85

umus

0.84

ridescent

0.84

čo

0.81

 pertenec

0.81

 Italijanski

0.79

 coraz

0.77

norms

0.77

Activations Density 0.007%

No Known Activations