© 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. 38596
    Prev
    Next
    INDEX
    Explanations

    data, work, question, information, claim

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

    This neuron strongly activates on isolated, capitalized single-word headings or section titles in the document.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ادم
    -1.41
     parfüm
    -1.28
     放題
    -1.27
     autre
    -1.24
    Новые
    -1.23
     groupBox
    -1.23
     concl
    -1.22
    ására
    -1.21
     火鍋
    -1.19
     hommage
    -1.18
    POSITIVE LOGITS
     who
    1.95
     necessary
    1.69
     It
    1.56
     Its
    1.52
     Again
    1.43
     its
    1.42
     again
    1.38
     same
    1.38
     terkait
    1.38
    Its
    1.36
    Activations Density 0.219%

    No Known Activations