© 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 · 124723 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
124723

INDEX

Explanations

location

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

⑉

-1.94

eſ

-1.66

篋

-1.60

roxene

-1.56

 übri

-1.55

 toalla

-1.55

 piccoli

-1.54

 サムネイル

-1.52

 quatrième

-1.51

 scrivere

-1.51

POSITIVE LOGITS

2.44

....

1.76

—

1.68

摟

1.68

in

1.66

You

1.66

1.63

...

1.62

1.61

他对

1.59

Activations Density 0.003%

No Known Activations