© 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. 34174
    Prev
    Next
    INDEX
    Explanations

    enum definition

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

    The neuron is highly sensitive to enumeration declarations (the “enum” keyword and related enum-definition syntax) in source 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
    igth
    -0.90
    ()]
    -0.87
     深
    -0.86
     quoque
    -0.84
    össä
    -0.83
     Jahrgang
    -0.82
     Αρχ
    -0.82
     blz
    -0.82
     ngôn
    -0.81
     پیشن
    -0.81
    POSITIVE LOGITS
     enum
    1.29
    enum
    1.07
    Enum
    0.96
     enums
    0.90
    enums
    0.90
    Alum
    0.87
    SCAR
    0.85
     when
    0.80
     öl
    0.78
     Enum
    0.77
    Activations Density 0.067%

    No Known Activations