© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110631
    Prev
    Next
    INDEX
    Explanations

    LaTeX fraction notation

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

    This neuron activates on LaTeX math‐mode function/structure commands (e.g. \frac, \sum, \limits, \sqrt) in the text.

    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
     simplistic
    -1.97
     undeniably
    -1.93
     if
    -1.82
     reduce
    -1.81
     particularly
    -1.81
     relentlessly
    -1.80
     allows
    -1.79
     sklo
    -1.79
     unequivocally
    -1.79
     promotes
    -1.77
    POSITIVE LOGITS
    .
    3.08
    probably
    1.96
    把她
    1.83
    four
    1.79
     ",
    1.76
    溌
    1.72
     dahil
    1.68
    better
    1.67
    five
    1.66
    -
    1.66
    Activations Density 0.009%

    No Known Activations