© 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. 99579
    Prev
    Next
    INDEX
    Explanations

    Monroe Community College, Automatic cardiac

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

    LaTeX markup indicating text within mathematical expressions, particularly with \text{...}.

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

    The neuron fires on LaTeX text‐formatting macros (e.g. \mbox, \text) embedded in math environments.

    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
    '
    -2.36
    >
    -2.09
    <
    -1.80
     \\
    -1.72
    ة
    -1.70
    "
    -1.70
     entonces
    -1.70
    \
    -1.66
     затем
    -1.66
     неболь
    -1.56
    POSITIVE LOGITS
    賔
    1.88
    瑧
    1.84
    There
    1.83
    when
    1.80
     when
    1.74
    there
    1.69
    élène
    1.62
     or
    1.62
    wości
    1.61
    ༘
    1.59
    Activations Density 0.001%

    No Known Activations