© 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. 22-GEMMASCOPE-RES-131K
    7. 38595
    Prev
    Next
    INDEX
    Explanations

    phrases with commas

    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
     薬局
    -1.83
     camiset
    -1.78
     pérd
    -1.77
     incrí
    -1.76
    鶿
    -1.73
    毟
    -1.72
     pernic
    -1.69
     ſol
    -1.68
    镲
    -1.66
    ኧ
    -1.65
    POSITIVE LOGITS
     will
    2.61
     which
    2.27
     or
    2.27
     should
    2.05
     have
    2.02
     has
    1.94
     would
    1.91
     including
    1.84
     are
    1.82
     can
    1.80
    Activations Density 0.064%

    No Known Activations