© 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. 85253
    Prev
    Next
    INDEX
    Explanations

    LaTeX operator declarations

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

    The neuron detects LaTeX math‐mode operator declarations and related commands (e.g. \DeclareMathOperator, \operatorname, \argmin).

    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
    üşonlu
    -2.75
     nurture
    -2.56
    抉
    -2.39
     If
    -2.36
    Reagents
    -2.34
     如果
    -2.34
    物体
    -2.28
    $.}
    -2.27
    蒾
    -2.25
    rasında
    -2.14
    POSITIVE LOGITS
    {
    3.05
    er
    2.86
    ate
    2.70
    k
    2.66
    龗
    2.47
    ,’
    2.45
    off
    2.39
     ck
    2.33
    ber
    2.30
    ’,
    2.27
    Activations Density 0.003%

    No Known Activations