© 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. 15645
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron is triggered by isolated numeric characters (digits or digit sequences) in technical/code tables or encoding listings.

    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
    '
    -1.73
    !";
    -1.51
     ...
    -1.51
    !",
    -1.48
     ">
    -1.45
     elit
    -1.45
     "¿
    -1.45
    !"
    -1.41
    !");
    -1.40
    "].
    -1.38
    POSITIVE LOGITS
     стаття
    1.69
     when
    1.52
     hábito
    1.46
    работа
    1.39
    ísticos
    1.38
    rainy
    1.37
     Вита
    1.34
     做法
    1.34
     that
    1.33
    МІ
    1.32
    Activations Density 0.060%

    No Known Activations