© 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. 34-GEMMASCOPE-RES-131K
    7. 117939
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

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

    The neuron is strongly activated by LaTeX control sequences—that is, backslashes and their following 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_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
    मुख
    -0.76
    cerpts
    -0.76
    šinou
    -0.75
    GOM
    -0.75
     occas
    -0.74
     الآخر
    -0.72
    orical
    -0.69
     Ceux
    -0.69
     liefde
    -0.69
    ستی
    -0.68
    POSITIVE LOGITS
    @
    1.09
    @@
    0.93
    InitVars
    0.90
     fontFamily
    0.90
    :@
    0.88
    埝
    0.88
     consulter
    0.88
     сьогодні
    0.86
    continues
    0.85
    @[
    0.84
    Activations Density 0.010%

    No Known Activations