© 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. 31927
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    Москва
    -0.73
    Fen
    -0.73
    ницу
    -0.72
    Цвет
    -0.71
     bunt
    -0.71
     uintptr
    -0.71
    США
    -0.71
    Bibliograf
    -0.71
     totalidad
    -0.70
    ichte
    -0.70
    POSITIVE LOGITS
     hive
    0.79
    戦士
    0.76
    \'
    0.75
     dira
    0.73
    diğini
    0.73
    nelles
    0.72
    idon
    0.71
     Striker
    0.71
     scher
    0.71
     acto
    0.71
    Activations Density 0.057%

    No Known Activations