© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48608
    Prev
    Next
    INDEX
    Explanations

    translatesAutoresizingMaskIntoConstraints

    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
    Vt
    -0.73
    isión
    -0.69
     Robbins
    -0.69
    EventHandler
    -0.66
     CITIES
    -0.65
    má
    -0.65
    דע
    -0.65
    Cody
    -0.65
    tly
    -0.63
    toolkit
    -0.63
    POSITIVE LOGITS
     kreeg
    0.70
     Amos
    0.68
    стройства
    0.65
    GB
    0.64
     ön
    0.62
    PLA
    0.61
    zessin
    0.61
    setFile
    0.60
    bner
    0.60
    $(\
    0.60
    Activations Density 0.077%

    No Known Activations