© 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. 22-GEMMASCOPE-RES-131K
    7. 26432
    Prev
    Next
    INDEX
    Explanations

    importing python modules

    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_22/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
     luxus
    -2.09
     kabát
    -1.95
     kompati
    -1.92
     実例
    -1.88
     kré
    -1.85
     histó
    -1.73
     importado
    -1.72
     pán
    -1.71
     広場
    -1.71
     排骨
    -1.71
    POSITIVE LOGITS
    v
    1.97
    m
    1.91
    C
    1.91
    V
    1.90
    n
    1.89
    f
    1.85
    c
    1.82
    L
    1.78
    M
    1.78
    w
    1.77
    Activations Density 0.023%

    No Known Activations