© 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. 65843
    Prev
    Next
    INDEX
    Explanations

    DO NOT EDIT

    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
     Васи
    -0.76
    DataContext
    -0.71
    WU
    -0.68
     свет
    -0.68
    Deal
    -0.67
     Lordships
    -0.67
    슷
    -0.67
    之
    -0.66
    illaries
    -0.65
    viť
    -0.65
    POSITIVE LOGITS
    ác
    0.71
    hp
    0.67
     lina
    0.66
    ंच
    0.64
     hp
    0.64
     HP
    0.63
     atlik
    0.63
    лосипе
    0.63
    伟大
    0.63
    HP
    0.61
    Activations Density 0.077%

    No Known Activations