© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49798
    Prev
    Next
    INDEX
    Explanations

    JavaScript code and text

    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
     АН
    -0.73
    cortico
    -0.73
    Undo
    -0.73
    brać
    -0.71
    Webb
    -0.71
     dwellings
    -0.71
    dahl
    -0.69
     workbook
    -0.69
     laiton
    -0.69
    缛
    -0.68
    POSITIVE LOGITS
    isAuthenticated
    0.74
    Compiled
    0.69
     飞
    0.67
     Geiger
    0.65
     Leon
    0.65
     Công
    0.64
    witz
    0.63
     rev
    0.63
    taca
    0.62
    кза
    0.61
    Activations Density 0.065%

    No Known Activations