© 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. 63026
    Prev
    Next
    INDEX
    Explanations

    directory / generator

    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
    assist
    -0.69
     assist
    -0.65
    عر
    -0.65
    住在
    -0.63
    dsi
    -0.62
     STEWART
    -0.62
    UITableViewCell
    -0.62
    获
    -0.61
     موسیقی
    -0.61
     Assist
    -0.60
    POSITIVE LOGITS
     Flax
    0.73
     Bax
    0.70
     xay
    0.66
     MONITORING
    0.66
     Clutch
    0.66
    رها
    0.65
    avait
    0.65
    therlands
    0.65
     Headline
    0.64
     flashing
    0.64
    Activations Density 0.048%

    No Known Activations