© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 113786 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
113786

INDEX

Explanations

attitudes toward

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

</strong>

-1.50

</b>

-1.45

我对

-1.44

 Anſ

-1.44

-1.43

nha

-1.39

ಞ

-1.38

 protože

-1.38

了吧

-1.34

🕗

-1.34

POSITIVE LOGITS

용

1.73

Thus

1.67

 бр

1.62

Therefore

1.59

 Tutto

1.53

 where

1.52

These

1.52

 всі

1.49



1.48

()

1.47

Activations Density 0.014%

No Known Activations