© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57283
    Prev
    Next
    INDEX
    Explanations

    date and revision information

    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
    Not in Any Lists

    No Comments

    Negative Logits
     acert
    -0.84
    หม
    -0.74
    ầng
    -0.73
     Sort
    -0.71
    رایط
    -0.70
     обслуживания
    -0.69
    撮影
    -0.67
     твер
    -0.66
     Punishment
    -0.66
     Stats
    -0.65
    POSITIVE LOGITS
     Campo
    0.75
    niksi
    0.71
     MainAxisSize
    0.68
    TreeView
    0.68
    缔
    0.68
    Campo
    0.67
    ktiv
    0.66
     sinar
    0.66
    utivo
    0.66
    щу
    0.66
    Activations Density 0.061%

    No Known Activations