© 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 · 104232 ｜ Neuronpedia

Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
104232

INDEX

Explanations

URL paths components

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

In

-1.49

-1.45

-1.37

 zwykle

-1.35

 Unlike

-1.34

 With

-1.31

 After

-1.30

 Then

-1.28

six

-1.27

has

-1.23

POSITIVE LOGITS

Aantal

1.90

焌

1.45

킁

1.41

extremely

1.38

 STARTED

1.37

उत्तर

1.35

甗

1.35

Οι

1.34

Už

1.34

܆

1.33

Activations Density 0.085%

No Known Activations