© 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. 12372
    Prev
    Next
    INDEX
    Explanations

    draw attention or source

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

    The neuron fires on occurrences of the verb “draw” (and its morphological variants like drawn, drawing).

    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
    ।
    0.66
     ذریع
    0.61
    সোমবার
    0.59
    崇
    0.58
    베이스
    0.57
     চাপে
    0.55
    ิ
    0.55
    ි
    0.55
    মঙ্গলবার
    0.54
    愍
    0.54
    POSITIVE LOGITS
     drawn
    1.58
     Draw
    1.47
     drew
    1.46
     draw
    1.45
    draw
    1.42
    drawn
    1.40
    Draw
    1.37
     Draws
    1.36
     dibujar
    1.31
     drawing
    1.29
    Activations Density 0.156%

    No Known Activations