© 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. 98765
    Prev
    Next
    INDEX
    Explanations

    sit and sit-related actions

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

    The neuron fires on any token containing the character sequence “sit” (e.g. “Sit,” “sit-,” “sitcom,” etc.).

    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
     of
    -2.97
    纥
    -2.75
    媄
    -2.72
    緜
    -2.67
    kwür
    -2.67
    橚
    -2.61
    ሷ
    -2.55
    姈
    -2.55
     fornecer
    -2.52
    some
    -2.48
    POSITIVE LOGITS
     `
    2.95
    </strong>
    2.88
    -
    2.83
    {
    2.77
     puzzling
    2.77
    [
    2.66
     hermosas
    2.63
     glaring
    2.55
     maravillosas
    2.55
     infused
    2.52
    Activations Density 0.005%

    No Known Activations