© 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 · 10-GEMMASCOPE-RES-131K · 72793 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
72793

INDEX

Explanations

thank you so much for

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

႐

-1.88

汌

-1.84

って何

-1.80

 TAMBIÉN

-1.62

 défaite

-1.62

 felicità

-1.58

 with

-1.49

ၠ

-1.46

 disfrute

-1.45

 következő

-1.45

POSITIVE LOGITS

是

1.53

<bos>

1.51

 estekak

1.49

 позволя

1.44

这

1.44

1.38

1.37

 Islas

1.34

依旧

1.34

1.34

Activations Density 0.003%

No Known Activations