© 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. 10-GEMMASCOPE-RES-131K
    7. 40381
    Prev
    Next
    INDEX
    Explanations

    boldface mathematical notation

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

    This neuron fires on LaTeX‐style mathematical notation—especially operator and variable commands (e.g. “\nabla,” “\mathbf,” function or vector names) within math expressions.

    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
     out
    -1.62
    纡
    -1.51
     می‌گو
    -1.51
    ⬈
    -1.46
     geweest
    -1.45
    ieť
    -1.41
    ăzi
    -1.38
    zość
    -1.37
    Highest
    -1.36
     quinze
    -1.34
    POSITIVE LOGITS
    これらの
    1.65
    無料で
    1.60
     a
    1.54
    戻る
    1.54
     Therefore
    1.52
    _
    1.39
    ⢊
    1.35
    jetivo
    1.32
     poži
    1.32
     Благодаря
    1.31
    Activations Density 0.005%

    No Known Activations