© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38682
    Prev
    Next
    INDEX
    Explanations

    female names and titles

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on occurrences of the proper name “Sophie.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    or
    -2.97
    m
    -2.89
     viſ
    -2.64
    　　“
    -2.53
    ﹐
    -2.47
    鬈
    -2.42
    .“
    -2.42
    ﹑
    -2.38
    “
    -2.34
    o
    -2.33
    POSITIVE LOGITS
    谁能
    2.75
     convertido
    2.72
    葑
    2.45
    はは
    2.44
    荩
    2.44
    你看
    2.44
    はな
    2.44
    哎呀
    2.44
    当时的
    2.36
     concentrado
    2.34
    Activations Density 0.003%

    No Known Activations