© 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. 10-GEMMASCOPE-RES-131K
    4. 104286
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    This neuron detects tokens that are part of mathematical expressions—especially variable names, subscripts, and other inline math symbols.

    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
     of
    -2.20
     have
    -1.80
    </strong>
    -1.77
     will
    -1.71
     at
    -1.68
    </h1>
    -1.59
     if
    -1.59
     kept
    -1.56
     consultato
    -1.52
     ones
    -1.51
    POSITIVE LOGITS
     certaines
    1.84
     temperat
    1.62
    鉭
    1.57
    ebly
    1.57
    硨
    1.56
    ~~~~~~~
    1.55
    蓠
    1.55
    刄
    1.54
    ≦
    1.53
    ✓
    1.48
    Activations Density 0.044%

    No Known Activations