© 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 · 45490 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
45490

INDEX

Explanations

plastic, plastics

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

plastics, packaging

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

 جوجل

0.44

瘸

0.43

给她

0.41

 tendered

0.40

స్‌

0.40

 علاج

0.40

▿

0.39

她的

0.39

 Ewing

0.38

 bothering

0.38

POSITIVE LOGITS

plas

0.50

 plastics

0.49

 Plastics

0.49

 plas

0.48

は

0.48

plastics

0.47

 Также

0.47

ør

0.45

 terminals

0.45

plastic

0.45

Activations Density 0.000%

No Known Activations