© 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. 92108
    Prev
    Next
    INDEX
    Explanations

    C code declarations and definitions

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

    The neuron is tuned to detect numeric literals (digit sequences) in the 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_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
     by
    -0.91
     class
    -0.85
    Class
    -0.84
     your
    -0.83
     Class
    -0.81
    getClass
    -0.81
    ˂
    -0.80
    ベント
    -0.78
    Фи
    -0.74
    אח
    -0.73
    POSITIVE LOGITS
    static
    2.25
     static
    1.93
     void
    1.55
    void
    1.45
    /**
    1.05
    inline
    1.05
     inline
    1.03
     EXPORT
    0.94
    INLINE
    0.94
    #
    0.94
    Activations Density 0.048%

    No Known Activations