© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 918
    Prev
    Next
    INDEX
    Explanations

    function definitions

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

    The neuron fires strongly on programming-definition keywords (e.g. “function,” “bool,” “def”), so it’s detecting lines that define or declare code elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programming keywords

    np_max-act-logits · claude-4-5-sonnetTriggered by @jrosseruk
    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
    Um
    0.49
    AE
    0.48
    这一
    0.48
    ;\
    0.47
    ;
    0.47
    IONS
    0.47
    Firefox
    0.46
    7
    0.46
    This
    0.46
    ﺏ
    0.46
    POSITIVE LOGITS
     pubblico
    0.51
     liderazgo
    0.50
     correcta
    0.48
     onRequest
    0.48
     courageous
    0.47
     principali
    0.47
     yılında
    0.46
     nombrado
    0.46
     displayName
    0.46
     uomini
    0.46
    Activations Density 0.000%

    No Known Activations