© 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. 1388
    Prev
    Next
    INDEX
    Explanations

    describing subtle actions or states

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

    The main thing this neuron does is detect descriptions of characters’ physical gestures and facial/body movements (e.g., gaze shifts, hand motions, blushes).

    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
     S
    0.79
    !
    0.70
    0.67
    J
    0.64
     L
    0.64
     J
    0.64
    v
    0.64
     AND
    0.63
     M
    0.61
     W
    0.61
    POSITIVE LOGITS
     abrazo
    0.86
     незна
    0.80
    👐
    0.80
     deoarece
    0.78
     стихо
    0.78
     слегка
    0.77
     debido
    0.77
     পুনরায়
    0.77
     garner
    0.76
     espalda
    0.76
    Activations Density 0.011%

    No Known Activations