© 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. 86458
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and definitions

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

    The neuron is strongly triggered by LaTeX/math‐mode syntax (dollar signs, backslashes, braces, and math‐style command names).

    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
     himself
    -2.05
     during
    -1.84
    7
    -1.73
    5
    -1.61
     at
    -1.60
     or
    -1.55
     then
    -1.55
    6
    -1.46
     on
    -1.41
    angkutan
    -1.39
    POSITIVE LOGITS
     linken
    1.61
     créativité
    1.55
     ljus
    1.55
     constater
    1.51
    לְ
    1.43
    Imagens
    1.43
    rierten
    1.43
    袛
    1.41
     ögon
    1.41
    erobic
    1.40
    Activations Density 0.112%

    No Known Activations