© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47415
    Prev
    Next
    INDEX
    Explanations

    Google open development

    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
     Jacksonville
    -0.77
     كوم
    -0.75
     Routes
    -0.71
    tainted
    -0.70
     Township
    -0.69
    reporting
    -0.69
    mybatis
    -0.68
     фур
    -0.68
    Friendly
    -0.68
     Retrieves
    -0.68
    POSITIVE LOGITS
     Reichen
    0.83
    obenz
    0.77
     cameras
    0.73
    ˅
    0.71
    قد
    0.71
    specifier
    0.68
    notation
    0.67
     getSession
    0.67
    ulose
    0.66
    MSO
    0.66
    Activations Density 0.046%

    No Known Activations