© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72594
    Prev
    Next
    INDEX
    Explanations

    fractions in mathematics

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

    The neuron is detecting LaTeX fraction commands (instances of “frac” in math mode).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     because
    -1.73
     if
    -1.72
     that
    -1.64
     for
    -1.56
     prevent
    -1.48
     undeniably
    -1.47
    Just
    -1.47
    There
    -1.46
     additional
    -1.45
     markedly
    -1.42
    POSITIVE LOGITS
    鼍
    1.41
     Dinas
    1.39
     magnific
    1.38
     apropri
    1.37
    wasn
    1.36
     SUGGEST
    1.35
     quintessential
    1.34
     ."
    1.34
     MAKES
    1.33
     crappy
    1.31
    Activations Density 0.006%

    No Known Activations