© 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. 15649
    Prev
    Next
    INDEX
    Explanations

    `----------` and `******` separators

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

    The neuron flags long runs of dash characters (sequence of “-”) used as separators or horizontal rules.

    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
    跸
    -2.47
     technically
    -2.28
     to
    -2.23
    癒し
    -2.08
     disminución
    -2.08
     sometime
    -2.05
    他自己
    -2.03
     proporciona
    -2.02
    落ち着いた
    -2.00
    粁
    -2.00
    POSITIVE LOGITS
     With
    2.39
     It
    2.28
     با
    2.20
    ния
    2.05
    with
    2.02
    峮
    2.02
    它
    1.97
    学校
    1.96
    when
    1.95
    тории
    1.95
    Activations Density 0.019%

    No Known Activations