© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69614
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron fires on code identifiers and parameter/field names—especially short uppercase acronyms or CamelCase tokens like IP, ID, Count, Delimiter, Cols, 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
     will
    -2.30
     would
    -1.81
     then
    -1.69
     should
    -1.66
     cannot
    -1.61
     in
    -1.51
     must
    -1.49
    (!__
    -1.44
     shall
    -1.43
     similarly
    -1.38
    POSITIVE LOGITS
     japonais
    1.49
     écou
    1.43
     réessayer
    1.41
    tismo
    1.36
     förra
    1.35
     sociala
    1.34
    gården
    1.34
     mengucap
    1.30
     permettant
    1.29
     jambes
    1.27
    Activations Density 0.056%

    No Known Activations