© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108783
    Prev
    Next
    INDEX
    Explanations

    equations and formulas

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

    This neuron detects the start of LaTeX display‐math environments (e.g. the “\begin{…}” lines for align, equation, array, cases, etc.).

    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
    ecks
    -0.94
    !("
    -0.87
    頎
    -0.84
    佞
    -0.83
     Pelosi
    -0.79
    żym
    -0.79
     насто
    -0.77
    あー
    -0.77
    bilang
    -0.76
    嗷
    -0.76
    POSITIVE LOGITS
     equation
    1.77
     equations
    1.66
    equation
    1.51
     Equations
    1.32
     Equation
    1.30
     formula
    1.27
     formulas
    1.09
    Equation
    1.09
     math
    1.06
     Formula
    1.05
    Activations Density 0.001%

    No Known Activations