© 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. 22-GEMMASCOPE-RES-131K
    7. 32752
    Prev
    Next
    INDEX
    Explanations

    specific terminology

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    扨
    -2.67
     "'");
    -2.47
    Ꮺ
    -2.44
     "'",
    -2.42
    憮
    -2.33
    能夠
    -2.31
    逕
    -2.31
    軔
    -2.22
     "'";
    -2.22
    名稱
    -2.22
    POSITIVE LOGITS
    '
    2.89
    ↵
    2.53
     "
    2.48
     of
    2.41
     
    2.31
     pembun
    2.27
    lgari
    2.05
    ですので
    1.98
     ("
    1.98
     '
    1.92
    Activations Density 0.304%

    No Known Activations