© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4930
    Prev
    Next
    INDEX
    Explanations

    ```csharp` or `object` declaration

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

    This neuron fires on object-oriented code constructs, especially Java class declarations and their inheritance/interface keywords (e.g. “class … extends … implements …”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    никами
    0.75
    strings
    0.73
    StringSet
    0.73
    unregister
    0.71
     если
    0.69
     строки
    0.68
    []}
    0.68
    그러나
    0.68
    token
    0.67
     когда
    0.67
    POSITIVE LOGITS
     IEquatable
    0.88
     StatefulWidget
    0.85
     prides
    0.82
     leverages
    0.72
     resists
    0.72
     specializes
    0.71
     implements
    0.71
     aspires
    0.71
     boasts
    0.70
     StatelessWidget
    0.70
    Activations Density 0.040%

    No Known Activations