© 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. 22-GEMMASCOPE-RES-131K
    7. 64595
    Prev
    Next
    INDEX
    Explanations

    integral and math notation

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

    The neuron fires on LaTeX‐style subscript or superscript markers (underscores or carets) followed by numbers in math expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     in
    -1.22
     so
    -1.22
    erobic
    -1.19
     from
    -1.12
     then
    -1.05
     by
    -1.04
    躾
    -1.04
     and
    -1.04
     even
    -1.03
    पाद
    -1.00
    POSITIVE LOGITS
     commencer
    1.25
     аккуратно
    1.15
     gewünschten
    1.13
    zości
    1.11
     sicherzustellen
    1.07
     listos
    1.06
     Lorsqu
    1.06
     folgendes
    1.05
     erforderlichen
    1.04
     bequem
    1.03
    Activations Density 0.000%

    No Known Activations