© 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. 64367
    Prev
    Next
    INDEX
    Explanations

    latex commands and packages

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

    The neuron is looking for short code‐ or markup‐style identifier tokens (e.g. small lowercase names in LaTeX package commands, XML attributes, header includes).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     on
    -2.34
     in
    -1.55
     by
    -1.47
     result
    -1.47
     through
    -1.38
     at
    -1.34
     with
    -1.31
     out
    -1.30
     from
    -1.28
     should
    -1.27
    POSITIVE LOGITS
    küche
    1.41
     dénon
    1.37
     mélanger
    1.36
    تصویر
    1.36
    vierno
    1.34
    essayer
    1.31
     refroid
    1.30
    Sonntag
    1.30
    مقدمه
    1.30
    tică
    1.30
    Activations Density 0.001%

    No Known Activations