© 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. 50498
    Prev
    Next
    INDEX
    Explanations

    XML namespaces 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
    邑
    -0.82
     haircuts
    -0.81
     Ordin
    -0.76
    ấy
    -0.75
     дру
    -0.75
    typeof
    -0.74
     Quite
    -0.74
    ####
    -0.74
    <0xA1>
    -0.71
    рог
    -0.71
    POSITIVE LOGITS
     fisuras
    0.78
     encontrou
    0.77
     หล
    0.76
     colocar
    0.76
    jiro
    0.75
     delightfully
    0.74
    ttt
    0.73
    UTI
    0.73
     nová
    0.72
     trabalho
    0.72
    Activations Density 2.241%

    No Known Activations