© 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. 110752
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structural elements

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

    The neuron detects the opening delimiters for LaTeX display‐style mathematics (e.g. “\[” or “$$”).

    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
     by
    -2.27
     ingenious
    -2.03
     even
    -1.99
     inglese
    -1.74
     belligerent
    -1.71
    火的
    -1.66
    Donativos
    -1.64
     незавер
    -1.63
     Often
    -1.63
     when
    -1.63
    POSITIVE LOGITS
    note
    1.88
    IN
    1.87
    non
    1.82
    pp
    1.80
    to
    1.78
     будет
    1.75
    will
    1.73
    na
    1.71
    ire
    1.70
    ю
    1.70
    Activations Density 0.018%

    No Known Activations