© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58887
    Prev
    Next
    INDEX
    Explanations

    latex document commands

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

    The neuron strongly activates on TeX “\begin{…” commands (e.g. “\begin{document}” or “\begin{forest}”) and on the “gov” tokens in URLs.

    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
     "
    -2.38
     but
    -2.25
    -
    -1.90
     ‘
    -1.88
     It
    -1.85
     amount
    -1.85
    a
    -1.77
     he
    -1.77
    begin
    -1.75
     is
    -1.71
    POSITIVE LOGITS
     wichtigste
    2.05
     \
    1.87
     點
    1.86
    땃
    1.84
    廕
    1.83
     sekä
    1.81
    茘
    1.79
     美術
    1.77
    ၟ
    1.74
    żeli
    1.73
    Activations Density 0.000%

    No Known Activations