© 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. 98650
    Prev
    Next
    INDEX
    Explanations

    ** documentation comments

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

    The neuron activates on long sequences of repeated whitespace or asterisk characters used as decorative or formatting elements (e.g. indented “****…” comment blocks).

    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
    ar
    -1.88
     some
    -1.85
     However
    -1.67
     of
    -1.65
     began
    -1.55
     แต่
    -1.53
    StartDate
    -1.38
     principais
    -1.38
     When
    -1.38
     The
    -1.38
    POSITIVE LOGITS
    Easily
    1.59
    Focusing
    1.56
    🟠
    1.55
     überprüft
    1.54
    Doing
    1.53
     Detal
    1.52
     Meksi
    1.49
    䉴
    1.48
     geda
    1.48
     lij
    1.48
    Activations Density 0.064%

    No Known Activations