© 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 · 22-GEMMASCOPE-RES-131K · 36472 ｜ Neuronpedia

Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
36472

INDEX

Explanations

javascript / typescript 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_22/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

These

-1.80

 This

-1.77

 电视

-1.75

They

-1.75

鼷

-1.74

 أيض

-1.73

Beskrivning

-1.73

-1.72

довать

-1.71

大さじ

-1.71

POSITIVE LOGITS

 that

1.78

埽

1.74

 tía

1.57

he

1.54

 vying

1.54

<strong>

1.50

 hoặc

1.50

↵

1.50

1.50

 hábit

1.48

Activations Density 0.005%

No Known Activations