© 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-2-27B · 22-GEMMASCOPE-RES-131K · 26566 | Neuronpedia
Home
Gemma-2-27B
22-GEMMASCOPE-RES-131K
26566
Prev
Next
MODEL
22-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
concessive though
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
The neuron fires on the discourse marker “though,” flagging that concessive conjunction.
oai_token-act-pair · o4-mini
Triggered by @jyhe0408
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-27b-pt-res/layer_22/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/22-gemmascope-res-131k/26566?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/22-gemmascope-res-131k/26566?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
見え
-1.30
אך
-1.27
แต่
-1.27
结束后
-1.20
wachen
-1.19
ạp
-1.14
óns
-1.12
嚷
-1.10
AllowAnonymous
-1.10
the
-1.09
POSITIVE LOGITS
.
1.70
'
1.62
5
1.55
0
1.43
6
1.30
3
1.29
The
1.25
7
1.22
,
1.20
:
1.20
Act
ivations
Density 0.009%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations