© 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. 40935
    Prev
    Next
    INDEX
    Explanations

    latex formatting commands

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

    The neuron fires on LaTeX formatting and markup tokens (e.g. control‐sequence names, math‐mode commands, font/style commands).

    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
    玘
    -2.06
    mazione
    -1.93
    𖤣
    -1.80
    zló
    -1.78
    柃
    -1.75
    馊
    -1.75
    驀
    -1.75
    鸰
    -1.74
     ocupado
    -1.74
    msford
    -1.73
    POSITIVE LOGITS
    .”
    2.33
    ”
    2.02
    –
    1.95
    ,
    1.78
    Well
    1.70
    ↵
    1.68
    We
    1.68
    看上去
    1.63
     necessario
    1.63
     zoude
    1.63
    Activations Density 0.182%

    No Known Activations