© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8971
    Prev
    Next
    INDEX
    Explanations

    constructor and initialization

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

    The neuron fires on API‐style documentation or code comments that describe creation or initialization operations (e.g. lines beginning with “Creates …” or detailing constructors/factory calls).

    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
     của
    0.63
     hài
    0.62
    뀌
    0.59
    纲
    0.58
     áo
    0.56
    mayın
    0.56
     nogle
    0.55
     naph
    0.55
    [\
    0.54
    [(\
    0.54
    POSITIVE LOGITS
     முன்ன
    0.63
    ガー
    0.63
     getInstance
    0.56
    Constructor
    0.54
    ینا
    0.54
    initializing
    0.54
     instantiation
    0.54
    出産
    0.54
     Constructor
    0.53
    スタンダード
    0.53
    Activations Density 0.007%

    No Known Activations