© 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
Home
Gemma-3-12B
24-GEMMASCOPE-2-RES-16K
40
Prev
Next
MODEL
24-gemmascope-2-res-16k
Source/SAE
INDEX
Go
Explanations
The neuron fires on verbs expressing cognitive stance or inference (e.g. “knew,” “conclude,” “argue,” “recognizing”), i.e. words that signal knowing or reasoning.
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/40?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/40?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
0.44
-
0.35
.
0.30
s
0.28
1
0.28
+
0.27
?
0.27
=
0.27
/
0.27
c
0.27
POSITIVE LOGITS
أنه
0.47
rằng
0.45
that
0.44
أنّ
0.44
أنها
0.43
که
0.40
दट
0.40
أن
0.39
ότι
0.39
bahwa
0.38
Act
ivations
Density 1.432%
Test
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations