© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78799
    Prev
    Next
    INDEX
    Explanations

    .c and .py file extensions

    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
     CT
    -0.75
     excelencia
    -0.73
     שנה
    -0.71
    后感
    -0.69
    orm
    -0.68
     xuất
    -0.68
    IBS
    -0.66
     centre
    -0.66
    .='
    -0.66
    堕
    -0.65
    POSITIVE LOGITS
     Arco
    0.74
    ニッシュ
    0.69
    olan
    0.69
     זכ
    0.68
     regata
    0.68
     bordeaux
    0.67
     Artillery
    0.67
    dispatch
    0.67
     Nome
    0.66
     Rheinland
    0.66
    Activations Density 0.098%

    No Known Activations