© 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. 22777
    Prev
    Next
    INDEX
    Explanations

    math and programming symbols

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

    The neuron fires on backslash characters that introduce LaTeX-style commands or math escape sequences.

    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
    2
    -3.16
     Ultimately
    -2.72
     Roughly
    -2.55
     With
    -2.55
     Because
    -2.53
    1
    -2.45
     According
    -2.39
     Those
    -2.33
     Although
    -2.31
     Despite
    -2.31
    POSITIVE LOGITS
    archiwizowane
    2.72
    缯
    2.66
    卺
    2.56
    䊐
    2.56
    粜
    2.41
    咴
    2.30
    苤
    2.22
    凊
    2.17
    肫
    2.13
    的价格
    2.08
    Activations Density 0.005%

    No Known Activations