© 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. 110984
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments and commands

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

    The neuron fires on the braces that delimit LaTeX environments or commands—i.e. the “{” and “}” tokens.

    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
    dique
    -0.79
    ђа
    -0.78
     Verlet
    -0.76
    ➻
    -0.76
    ی
    -0.76
     cams
    -0.76
    kko
    -0.75
    letti
    -0.74
     microfiber
    -0.73
     Diff
    -0.71
    POSITIVE LOGITS
     equation
    1.29
     equations
    1.20
     aligned
    0.96
     formulas
    0.90
     mathematics
    0.88
    REQUIREMENTS
    0.84
     aligning
    0.84
     math
    0.83
     alignment
    0.83
     аса
    0.83
    Activations Density 0.002%

    No Known Activations