© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128211
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on programming “call” syntax—that is, tokens involved in function or method invocations (parentheses-driven calls, trailing semicolons, template-literal/backtick calls, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    closing code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -1.07
     area
    -1.01
     is
    -0.95
     primary
    -0.95
     /
    -0.92
     Sh
    -0.92
     --
    -0.91
      
    -0.91
     from
    -0.89
     your
    -0.88
    POSITIVE LOGITS
    Zubereitung
    1.11
    bình
    1.07
    confident
    1.04
    皝
    1.02
     wyniki
    1.01
    Kolor
    1.01
     TOGETHER
    1.00
    trường
    1.00
    静岡
    0.99
     ček
    0.99
    Activations Density 0.013%

    No Known Activations