© 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. 15607
    Prev
    Next
    INDEX
    Explanations

    expressing no idea

    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
     dreaded
    -2.33
     便利
    -2.30
    嚶
    -2.22
     宣传
    -2.17
    宬
    -2.16
     carrinho
    -2.11
     階段
    -2.03
    鸰
    -2.03
     enviados
    -2.02
     notorious
    -2.00
    POSITIVE LOGITS
    ing
    2.03
     he
    1.99
    .
    1.95
     of
    1.86
    ?
    1.82
    “
    1.78
     
    1.77
    Ꮮ
    1.77
    romas
    1.71
     Our
    1.67
    Activations Density 0.005%

    No Known Activations