© 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 · 47536 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
47536

INDEX

Explanations

c++ standard library data structures

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

Of

-1.79

⃙

-1.70

 EconPapers

-1.69

 první

-1.64

 lascia

-1.64

癀

-1.63

ösungen

-1.63

荩

-1.62



-1.60

 resulting

-1.59

POSITIVE LOGITS

鱨

1.93

菇

1.80

炖

1.74

ably

1.64

麃

1.60

the

1.59

你

1.59

 休閒

1.58

 saveiro

1.55

灕

1.54

Activations Density 0.007%

No Known Activations