© 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. 65797
    Prev
    Next
    INDEX
    Explanations

    http urls and licenses

    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
     СА
    -0.70
    ><!--
    -0.69
    ودي
    -0.68
     modulus
    -0.68
    ","","
    -0.68
    ља
    -0.68
    滝
    -0.68
     resultSet
    -0.66
    Back
    -0.65
    igus
    -0.65
    POSITIVE LOGITS
     campaigns
    0.80
    ċċ
    0.78
     campaign
    0.73
    wala
    0.73
    Ễ
    0.67
     Consultado
    0.66
     кампа
    0.65
    idades
    0.64
    vater
    0.64
    OGN
    0.64
    Activations Density 0.061%

    No Known Activations