© 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. 34-GEMMASCOPE-RES-131K
    7. 58042
    Prev
    Next
    INDEX
    Explanations

    C++ code structure declarations

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

    The neuron fires on numeric literals in source 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
    剽
    -0.85
     behöver
    -0.83
     område
    -0.81
    ˂
    -0.81
    året
    -0.81
    días
    -0.80
     Neri
    -0.80
    דול
    -0.78
     christmas
    -0.77
     arbete
    -0.76
    POSITIVE LOGITS
    class
    1.66
     class
    1.42
    inline
    1.34
    template
    1.34
    }
    1.21
    struct
    1.19
    void
    1.09
     void
    1.05
     template
    1.05
    ";}
    1.05
    Activations Density 0.070%

    No Known Activations