© 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. 119535
    Prev
    Next
    INDEX
    Explanations

    enums and enumerations

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

    the word "Enums" or "Enumeration" in programming code contexts.

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

    The neuron fires on occurrences of “enum” or related forms (like Enums, Enumerations) 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_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
     ſte
    -2.41
     ſta
    -2.38
    潆
    -2.33
    ]");
    -2.31
    </em>
    -2.23
    ون
    -2.16
     apprécié
    -2.14
    zeichnete
    -2.13
    荭
    -2.09
    __))
    -2.08
    POSITIVE LOGITS
     in
    2.19
    on
    2.14
     anuales
    2.11
    ERS
    2.11
     and
    2.08
     
    1.97
    an
    1.95
    .”
    1.90
     Allowing
    1.89
     Lots
    1.88
    Activations Density 0.001%

    No Known Activations