© 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. 34-GEMMASCOPE-RES-131K
    7. 56883
    Prev
    Next
    INDEX
    Explanations

    command or target

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     INTERESAR
    -0.74
    CLP
    -0.73
     Papa
    -0.72
    ENAME
    -0.72
    WZ
    -0.71
     RoutedEventArgs
    -0.71
     וגם
    -0.70
     информация
    -0.70
    كو
    -0.70
    ローズ
    -0.69
    POSITIVE LOGITS
     flattening
    0.83
    rento
    0.82
     flatten
    0.80
     festival
    0.76
     tumbuh
    0.74
    flatten
    0.73
     flattened
    0.72
     preserve
    0.72
     leveled
    0.72
    ruzzo
    0.71
    Activations Density 0.060%

    No Known Activations