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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54043
    Prev
    Next
    INDEX
    Explanations

    code, version, and file 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
    Tazama
    -0.77
    setFrom
    -0.77
     FROM
    -0.71
    FROM
    -0.69
    utang
    -0.67
    虽
    -0.67
    ulsion
    -0.66
    QLabel
    -0.65
    行政区划
    -0.65
    tillation
    -0.64
    POSITIVE LOGITS
    Xia
    0.92
     Xia
    0.87
    twenty
    0.79
    广
    0.73
     twenty
    0.70
     Zur
    0.68
    Twenty
    0.68
     feas
    0.66
     zoomed
    0.66
    ָׁ
    0.65
    Activations Density 0.241%

    No Known Activations