© 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. 10-GEMMASCOPE-RES-131K
    7. 38902
    Prev
    Next
    INDEX
    Explanations

    currently being

    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
     Einige
    -1.79
    していない
    -1.73
     其他
    -1.72
     opravdu
    -1.72
     creeping
    -1.70
    邶
    -1.70
     aldrig
    -1.65
    荅
    -1.64
     of
    -1.56
     قوی
    -1.55
    POSITIVE LOGITS
    ’
    2.48
    ?”
    2.25
     that
    2.00
    ”
    1.86
     to
    1.80
    ...”
    1.77
    —”
    1.73
    standigheden
    1.69
    ();)
    1.69
    —“
    1.68
    Activations Density 1.236%

    No Known Activations