© 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. 10-GEMMASCOPE-RES-131K
    7. 85954
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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
    Čes
    -1.77
     Scritto
    -1.76
    ＊＊＊＊
    -1.70
    TAINS
    -1.66
     hebben
    -1.66
    先日
    -1.64
    今年の
    -1.64
    などなど
    -1.63
    本日は
    -1.62
     Италии
    -1.62
    POSITIVE LOGITS
     of
    2.70
     also
    2.23
     and
    1.89
     (
    1.74
     who
    1.69
     This
    1.63
     The
    1.63
    ↵↵
    1.56
     which
    1.54
     ebenfalls
    1.52
    Activations Density 0.014%

    No Known Activations