© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1811
    Prev
    Next
    INDEX
    Explanations

    sorting array logic

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

    The neuron fires on floating‐point numeric literals (decimal numbers) embedded in code or log‐style text.

    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_31_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
    //
    0.65
    //
    0.58
     வர
    0.57
     紹介
    0.56
     //[
    0.56
     মিশর
    0.55
    /*
    0.54
     bieden
    0.54
     券
    0.54
    ,}$
    0.53
    POSITIVE LOGITS
    elif
    0.94
     elif
    0.93
    classmethod
    0.82
     def
    0.65
    else
    0.62
    numpy
    0.60
    妷
    0.60
     else
    0.59
    laki
    0.57
     হা
    0.57
    Activations Density 0.008%

    No Known Activations