© 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. 10-GEMMASCOPE-RES-131K
    7. 128097
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

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

    This neuron activates on bits of LaTeX‐style mathematical notation (variables, operators, and formula tokens within 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_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
     meticulous
    -2.03
    沨
    -2.02
     TWO
    -1.92
     zahlreiche
    -1.78
    ſelves
    -1.76
     angebra
    -1.76
     dazzling
    -1.75
     rigorous
    -1.74
     cheerful
    -1.73
     exuberant
    -1.73
    POSITIVE LOGITS
     recounts
    1.98
     quando
    1.90
    といふ
    1.82
     they
    1.77
    ዣ
    1.73
    蕓
    1.70
    ⢕
    1.68
     debacle
    1.67
     ก็
    1.62
    PASO
    1.62
    Activations Density 0.010%

    No Known Activations