© 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. 34-GEMMASCOPE-RES-131K
    7. 48152
    Prev
    Next
    INDEX
    Explanations

    enum values and types

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

    This neuron fires on enum‐related constructs—i.e. the `enum` keyword, EnumSet/EnumSet.of calls, enum declarations, and enum constant names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     hayas
    -0.92
    Monitoring
    -0.86
     jornal
    -0.86
    century
    -0.85
     fonctionnent
    -0.84
     APPELLANT
    -0.84
    acité
    -0.83
     Dalio
    -0.81
    Daha
    -0.80
     minOccurs
    -0.80
    POSITIVE LOGITS
     valueOf
    1.04
    Enum
    1.03
     bestellen
    0.98
    EnumValue
    0.93
     значения
    0.90
     values
    0.87
     Enum
    0.86
     members
    0.85
    是非常
    0.84
     enum
    0.83
    Activations Density 0.017%

    No Known Activations