© 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. 90844
    Prev
    Next
    INDEX
    Explanations

    latex commands and symbols

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

    This neuron detects LaTeX-style brace sequences (e.g. tokens like “]{”, “[d]{”, or section markers with “{” and “}”).

    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
     koti
    -0.84
     VOR
    -0.74
    ДУ
    -0.70
    weakSelf
    -0.70
     Jahrh
    -0.69
    ----------
    -0.69
    unyai
    -0.69
     famili
    -0.69
    freund
    -0.69
     quinto
    -0.69
    POSITIVE LOGITS
    http
    1.03
     http
    0.86
    izzy
    0.84
    https
    0.82
     Southland
    0.79
     déput
    0.78
    去吧
    0.78
     furious
    0.78
     https
    0.77
    ターン
    0.77
    Activations Density 0.001%

    No Known Activations