© 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. 98708
    Prev
    Next
    INDEX
    Explanations

    wedding

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

    The neuron fires on mentions of “wedding” (including plural and inflected forms).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     aDecoder
    -1.76
    have
    -1.76
    th
    -1.74
     HISTORY
    -1.73
    в
    -1.72
    lijks
    -1.71
     wunderbar
    -1.70
     THINGS
    -1.67
    $.
    -1.67
    ción
    -1.67
    POSITIVE LOGITS
    姈
    1.91
     Our
    1.84
     We
    1.80
     weddings
    1.71
    狲
    1.69
     véritable
    1.63
     My
    1.63
    灕
    1.61
     récemment
    1.61
     other
    1.57
    Activations Density 0.014%

    No Known Activations