© 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 · 11848 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
11848

INDEX

Explanations

to log

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

 GRATU

-1.59

 QUÉ

-1.55

菒

-1.54

 obicei

-1.52

it

-1.43

 abiye

-1.43

 politika

-1.42

éroport

-1.41

 they

-1.40

 greu

-1.39

POSITIVE LOGITS

 other

1.52

or

1.45

1.41

of

1.41

年来

1.38

is

1.35

 recientemente

1.35

 recently

1.34

 comienzo

1.32

迥

1.32

Activations Density 0.041%

No Known Activations