© 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. 22656
    Prev
    Next
    INDEX
    Explanations

    <b> tags

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

    This neuron is triggered by HTML markup tags (especially bold/strong tags).

    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
     where
    -2.44
     with
    -2.06
     by
    -1.95
     as
    -1.71
     or
    -1.69
    d
    -1.68
     has
    -1.65
     that
    -1.61
     from
    -1.59
     in
    -1.56
    POSITIVE LOGITS
    鹩
    2.14
    泐
    1.89
    튿
    1.77
    鯷
    1.72
    鯢
    1.69
    我が家の
    1.65
    齜
    1.65
    烔
    1.64
     唯美
    1.64
     essayé
    1.60
    Activations Density 0.159%

    No Known Activations