© 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. 130806
    Prev
    Next
    INDEX
    Explanations

    LaTeX package usage

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

    The neuron is triggered by LaTeX command names (e.g. documentclass, usepackage, includegraphics).

    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
    A
    -2.39
    h
    -2.31
     
    -2.30
    <em>
    -2.22
     also
    -2.08
    '
    -2.03
    -
    -2.02
    ()
    -1.90
    o
    -1.82
    ”
    -1.82
    POSITIVE LOGITS
    引用元
    1.94
    emporio
    1.89
    RemindMe
    1.80
    lerinden
    1.77
    INCLUDING
    1.77
    acknow
    1.74
    продам
    1.73
    Muerte
    1.73
     قاعده
    1.73
     every
    1.71
    Activations Density 0.004%

    No Known Activations