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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81690
    Prev
    Next
    INDEX
    Explanations

    programming keywords and identifiers

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

    The neuron responds to code‐specific identifiers and technical tokens (names, functions, compiler directives, etc.) in programming or configuration files.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -1.56
     because
    -1.56
     with
    -1.31
    wym
    -1.28
     within
    -1.20
     using
    -1.19
     regardless
    -1.18
     often
    -1.17
    Dá
    -1.16
     at
    -1.16
    POSITIVE LOGITS
    ۔
    1.30
     alcune
    1.28
     gigantic
    1.27
     verschiedenen
    1.25
     verschillende
    1.24
    ౮
    1.23
     diversos
    1.22
    龵
    1.22
    ｒ
    1.22
     MICHAEL
    1.21
    Activations Density 0.033%

    No Known Activations