© 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. 10-GEMMASCOPE-RES-131K
    7. 42774
    Prev
    Next
    INDEX
    Explanations

    AREA_ OPTION_ STORAGE_WRITER

    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_10/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
    s
    -3.20
    u
    -3.19
    *
    -3.02
    وضح
    -2.98
     or
    -2.83
    o
    -2.81
     then
    -2.56
    er
    -2.52
    es
    -2.45
     if
    -2.45
    POSITIVE LOGITS
    CHREIB
    3.28
    dci
    2.91
    ſelf
    2.83
    ︲
    2.77
    selbe
    2.75
    攫
    2.67
    骉
    2.64
    vantaged
    2.63
    muerzo
    2.59
     inginkan
    2.55
    Activations Density 0.130%

    No Known Activations