© 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. 64205
    Prev
    Next
    INDEX
    Explanations

    Excel spreadsheets

    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
    がなく
    -0.79
    Longitud
    -0.79
     Chính
    -0.75
    Complaint
    -0.73
    ختلف
    -0.71
    sampled
    -0.70
    訊息
    -0.69
    knights
    -0.69
    sakura
    -0.68
    uluş
    -0.68
    POSITIVE LOGITS
     spreadsheet
    3.86
     Excel
    3.83
     excel
    3.45
    Excel
    3.14
     spreadsheets
    3.08
    excel
    2.95
    spreadsheet
    2.47
    xlsx
    2.45
     csv
    2.44
    xls
    2.39
    Activations Density 0.073%

    No Known Activations