© 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. 2892
    Prev
    Next
    INDEX
    Explanations

    POST request parameters

    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
     публикации
    -0.77
    lante
    -0.75
    gany
    -0.73
    ancho
    -0.70
    Dp
    -0.70
     lej
    -0.69
     Spraw
    -0.68
     dp
    -0.66
    angela
    -0.66
     konsek
    -0.66
    POSITIVE LOGITS
     Beckett
    0.72
    يره
    0.70
    鈑
    0.65
     kept
    0.65
     diurnal
    0.64
    لاه
    0.63
    xDB
    0.63
    reys
    0.63
     multifaceted
    0.63
    шенные
    0.62
    Activations Density 0.067%

    No Known Activations