© 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 · 41367 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
41367

INDEX

Explanations

names followed by surnames

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

íme

-1.48

 again

-1.46

 たち

-1.45

 couvercle

-1.45

 then

-1.36

 aree

-1.36

⻓

-1.36

 chêne

-1.35

 SITY

-1.34

 thereafter

-1.30

POSITIVE LOGITS

？』

1.41

an

1.38

 That

1.35

Two

1.35

1.34

1.34

迺

1.33

How

1.31

 Seems

1.31

1.29

Activations Density 0.061%

No Known Activations