© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
GEMMA-3-12B · 24-GEMMASCOPE-2-RES-16K · 9109 ｜ Neuronpedia
Home
Gemma-3-12B
24-GEMMASCOPE-2-RES-16K
9109
Prev
Next
MODEL
24-gemmascope-2-res-16k
Source/SAE
INDEX
Go
Explanations
LLM world
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
The neuron strongly activates on abstract, formal nouns (especially those ending in ‑ion, ‑ity, ‑ure, etc.) that appear in legal or technical contexts.
oai_token-act-pair · o4-mini
Triggered by @jyhe0408
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
How To Load
Prompts (Dashboard)
392,802 prompts, 256 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-3-12b/24-gemmascope-2-res-16k/9109?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-3-12b/24-gemmascope-2-res-16k/9109?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
২১
0.73
২২
0.68
২৩
0.68
./
0.65
isted
0.63
ಸುಬ್ಬ
0.63
ล่ะ
0.62
μορ
0.61
zego
0.61
@
0.59
POSITIVE LOGITS
이지만
1.14
ですが
1.13
だが
1.05
ませんが
1.05
但不
1.02
지만
1.00
لكن
0.99
しますが
0.98
लेकिन
0.95
but
0.95
Act
ivations
Density 0.395%
Test
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
