© 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. 22-GEMMASCOPE-RES-131K
    7. 128007
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens within or immediately surrounding quoted dialogue, effectively detecting when a character is speaking.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    opening phrases or quotes

    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
    tabControl
    -1.10
    Начало
    -1.05
     ――
    -1.02
    schrift
    -0.98
     koment
    -0.96
    uded
    -0.93
    sandalia
    -0.93
    messageId
    -0.93
    蕺
    -0.91
     fà
    -0.90
    POSITIVE LOGITS
    明明
    0.95
    0.93
    resas
    0.93
    !
    0.93
    wną
    0.91
    <u>
    0.90
     فقال
    0.89
    虔
    0.88
    ,”
    0.85
     выде
    0.85
    Activations Density 0.025%

    No Known Activations