© 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. 34-GEMMASCOPE-RES-131K
    7. 99145
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical and chemical notation

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

    LaTeX mathematical notation and special typesetting commands in technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by markup and code‐like tokens—e.g. LaTeX commands, braces, URLs, and other formatting/code fragments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     netto
    -0.79
     oid
    -0.78
    Xen
    -0.77
     identities
    -0.76
    Zor
    -0.75
    規劃
    -0.73
     cô
    -0.73
     Nobles
    -0.72
     Ura
    -0.72
     iyo
    -0.72
    POSITIVE LOGITS
    displaystyle
    1.20
     display
    1.02
     Display
    1.00
    estyle
    0.98
    Display
    0.97
     text
    0.91
    text
    0.86
     Зачем
    0.84
     Desde
    0.83
     escritório
    0.80
    Activations Density 0.001%

    No Known Activations