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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82663
    Prev
    Next
    INDEX
    Explanations

    LaTeX \usepackage command

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

    The neuron fires on LaTeX preamble lines that declare the document class or load packages (e.g. “\documentclass” and “\usepackage”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     квітня
    -0.81
    psfrag
    -0.81
     Anterior
    -0.80
     ακόμα
    -0.80
     either
    -0.80
     وزارة
    -0.80
     confirmed
    -0.78
    ----</
    -0.77
    -------------</
    -0.77
     Subsequently
    -0.74
    POSITIVE LOGITS
     {
    0.97
     Threats
    0.96
     colores
    0.87
    Akan
    0.87
     čierna
    0.85
    Bukan
    0.84
    Werde
    0.84
    atime
    0.83
    rpura
    0.82
    ∬
    0.82
    Activations Density 0.003%

    No Known Activations