© 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-3-27B · 31-GEMMASCOPE-2-RES-262K · 39816 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
39816

INDEX

Explanations

communications

np_acts-logits-general · gemini-2.5-flash-lite

conditional logic and ai

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 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

 uptime

0.42

結構

0.41

機種

0.39

帕

0.38

 annexation

0.38

胎

0.38

lá

0.37

termination

0.37

釀

0.37

籠

0.37

POSITIVE LOGITS

 Verw

0.50



0.50

 Один

0.49

 Почему

0.48

 Tìm

0.48

actifs

0.48

>]

0.47

istos

0.46

ழ்ப

0.45

۲۰

0.45

Activations Density 0.000%

No Known Activations