© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 24897
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and mathematical notation

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

    The neuron fires on LaTeX macro‐definition commands (e.g. “\def…”, “\DeclareMathOperator…”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     podría
    -1.01
     facade
    -0.97
     mungkin
    -0.96
     inaweza
    -0.95
     is
    -0.93
    struzione
    -0.93
    care
    -0.91
     poate
    -0.90
     potrebbe
    -0.90
     lmao
    -0.89
    POSITIVE LOGITS
    Shortly
    1.20
    VING
    1.09
    灕
    1.09
    Numerous
    1.09
     Shortly
    1.08
    ampaikan
    1.05
    contrar
    1.05
     suitable
    1.05
     magasiner
    1.05
    ruptedException
    1.04
    Activations Density 0.001%

    No Known Activations