© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58196
    Prev
    Next
    INDEX
    Explanations

    code blocks and math structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Embeds
    IFrame
    Link
    Negative Logits
    '
    -3.64
    s
    -3.20
     
    -2.98
    \
    -2.95
    er
    -2.52
    (
    -2.50
     are
    -2.50
     –
    -2.42
    i
    -2.33
    ↵
    -2.28
    POSITIVE LOGITS
    }{
    3.27
    珦
    3.20
    Ꭳ
    3.06
    趼
    3.03
    
    2.77
    凩
    2.75
    
    2.73
    塍
    2.72
    迓
    2.66
    鶺
    2.63
    Activations Density 0.007%

    No Known Activations