© 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-2-27B
10-GEMMASCOPE-RES-131K
7099
Prev
Next
MODEL
10-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
adverbs of excess
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
The neuron activates on the adverb “overly,” flagging that specific intensifier.
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-27b-pt-res/layer_10/width_131k
Prompts (Dashboard)
24,576 prompts, 128 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-2-27b/10-gemmascope-res-131k/7099?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-2-27b/10-gemmascope-res-131k/7099?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
ar
-2.36
is
-2.33
AND
-2.31
较大
-2.28
to
-2.27
at
-2.25
\
-2.19
of
-2.17
および
-2.16
její
-2.16
POSITIVE LOGITS
1
3.06
7
2.47
,’
2.34
䊏
2.30
This
2.28
これは
2.25
8
2.22
侂
2.20
2.20
ανθρώ
2.20
Act
ivations
Density 0.002%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
