© 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. 34-GEMMASCOPE-RES-131K
    7. 3462
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with symbols

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

    The neuron strongly activates for symbols and tokens rich in punctuation—especially parentheses, operators (&&, ||, /, *, etc.), and other non‐alphanumeric code/math tokens.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     there
    -0.94
     may
    -0.90
    dingen
    -0.88
    ;
    -0.87
     first
    -0.86
     confident
    -0.85
     sufferers
    -0.84
    There
    -0.84
    EXT
    -0.82
    iegel
    -0.80
    POSITIVE LOGITS
     apology
    0.88
    agie
    0.87
    WriteLiteral
    0.84
     isKindOfClass
    0.81
    tiktok
    0.81
     isEqualToString
    0.81
    🚺
    0.79
     ingresos
    0.79
    reloadData
    0.79
     récol
    0.76
    Activations Density 0.030%

    No Known Activations