© 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. 10-GEMMASCOPE-RES-131K
    7. 15652
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with n

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

    The neuron is primarily triggered by LaTeX/math‐mode tokens (backslashes and the commands that follow them).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     a
    -1.72
     the
    -1.42
     erfolgre
    -1.23
     everything
    -1.22
    (({
    -1.21
     acheteurs
    -1.21
     certain
    -1.19
    ！！！”
    -1.19
     koning
    -1.13
     connues
    -1.12
    POSITIVE LOGITS
    </h3>
    1.72
    </h5>
    1.35
    0
    1.33
     extraordin
    1.30
    Flug
    1.29
    ƌ
    1.29
    uniqlo
    1.25
    Ещё
    1.24
    initialise
    1.21
    ཫ
    1.21
    Activations Density 0.017%

    No Known Activations