© 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. 22-GEMMASCOPE-RES-131K
    7. 12930
    Prev
    Next
    INDEX
    Explanations

    programming keywords and subsequent identifiers

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

    This neuron detects identifiers used as function or class names (i.e. names of functions, methods, constructors, or classes) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     
    -1.63
     on
    -1.60
     is
    -1.51
     you
    -1.46
     by
    -1.36
     others
    -1.35
     his
    -1.34
     in
    -1.26
     have
    -1.23
     be
    -1.22
    POSITIVE LOGITS
    Angebot
    1.77
    Themen
    1.63
    Inhalte
    1.53
    Liefer
    1.49
    Bereich
    1.46
    Various
    1.45
    Numerous
    1.41
    När
    1.39
    Also
    1.38
    Furthermore
    1.38
    Activations Density 0.014%

    No Known Activations