© 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 · 10-GEMMASCOPE-RES-131K · 99478 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
99478

INDEX

Explanations

of course

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_10/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

by

-1.54

 Exteriores

-1.52

 each

-1.51

Each

-1.49

了承

-1.44

why

-1.43

それが

-1.41

it

-1.40

 WHETHER

-1.35

他的

-1.33

POSITIVE LOGITS

昳

1.64

 racconta

1.59

 constater

1.58

 provinciale

1.55

 мечты

1.52

arschu

1.52

끫

1.51

 balcon

1.50

￪

1.48

 semaines

1.45

Activations Density 0.004%

No Known Activations