© 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. 10-GEMMASCOPE-RES-131K
    7. 101553
    Prev
    Next
    INDEX
    Explanations

    go language keywords

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

    type declarations and parameters in Go programming language code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on code tokens that include digits—e.g. sized types (uint64, float32), numeric literals, array‐length brackets, etc.

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

    No Comments

    Negative Logits
     that
    -2.33
     which
    -1.98
    _
    -1.85
    ské
    -1.69
     to
    -1.69
     a
    -1.68
     being
    -1.65
     having
    -1.60
    -
    -1.55
     betek
    -1.50
    POSITIVE LOGITS
     acompañado
    1.69
    ENTINA
    1.65
     escuchar
    1.61
     commento
    1.58
     recib
    1.57
     encabez
    1.55
     précédemment
    1.55
    opress
    1.54
     службу
    1.50
    还是要
    1.49
    Activations Density 0.036%

    No Known Activations