© 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. 6815
    Prev
    Next
    INDEX
    Explanations

    media items in lists

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

    The neuron is basically detecting the token “book” (and its variants like “books,” “BookList,” etc.) in code or markup.

    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
    ineno
    -1.52
    क्या
    -1.50
    нении
    -1.50
     pamamagitan
    -1.41
     \%$
    -1.39
    ünde
    -1.37
    ༀ
    -1.37
     historia
    -1.37
     famosas
    -1.36
    哒
    -1.36
    POSITIVE LOGITS
    Neither
    1.75
    How
    1.73
    りする
    1.67
    2
    1.62
    Having
    1.61
    Trying
    1.59
     mógł
    1.59
    <
    1.56
    If
    1.54
    {
    1.53
    Activations Density 0.024%

    No Known Activations