© 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 · 118983 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
118983

INDEX

Explanations

text and following words

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

’

-3.33

-2.72

-2.28

”

-1.96

随着

-1.91

朦

-1.86

-1.84

 ваше

-1.84

,”

-1.80

-1.78

POSITIVE LOGITS

"}}>

2.53

 unangemess

2.42

檮

2.33

इटम

2.17

 posteriores

2.14

 rękaw

2.13

௮

2.06

 Konsequ

2.05



2.05

 numerosos

2.03

Activations Density 0.077%

No Known Activations