© 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
70908
Prev
Next
MODEL
10-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
how many or how much
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
The neuron fires strongly on “how” emphasis constructions—especially the phrase “just how” (as in “just how much…”).
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_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/70908?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/70908?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
</h3>
-2.70
).
-2.14
']
-1.99
)
-1.98
࿊
-1.86
-1.84
")
-1.79
還可以
-1.73
黽
-1.70
"),
-1.69
POSITIVE LOGITS
しました
1.93
не
1.73
how
1.72
姑娘
1.67
jsou
1.63
idades
1.55
'=>
1.55
',
1.52
he
1.52
忘了
1.50
Act
ivations
Density 0.004%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations