© 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. 26597
    Prev
    Next
    INDEX
    Explanations

    enumeration types and data classifications

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

    The neuron fires on the syntax of enum declarations (the keyword “enum” and its following brackets) 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
    ঊ
    -0.95
     ДЛЯ
    -0.88
    Atle
    -0.84
    unches
    -0.84
    makeatletter
    -0.84
     väga
    -0.80
     developer
    -0.80
     breweries
    -0.78
    𝗞
    -0.78
    lysses
    -0.77
    POSITIVE LOGITS
     choices
    1.20
     choice
    1.06
     whether
    1.04
    Enum
    1.01
     again
    1.00
     enum
    0.98
    ENUM
    0.95
     options
    0.94
    YesNo
    0.90
     type
    0.88
    Activations Density 0.010%

    No Known Activations