© 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. 12809
    Prev
    Next
    INDEX
    Explanations

    sleep and circadian rhythms

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

    The neuron activates on mentions of sleep disturbances and related medical symptoms (e.g., chronic fatigue, waking up repeatedly, sleep apnea).

    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
    Coat
    0.61
    コート
    0.60
     Coat
    0.59
    etano
    0.59
     Dough
    0.59
    挎
    0.58
    coat
    0.58
    靱
    0.58
    OA
    0.57
     উত্তরাধ
    0.57
    POSITIVE LOGITS
     sleep
    1.92
     Sleep
    1.84
    Sleep
    1.84
    睡眠
    1.76
    sleep
    1.66
     ngủ
    1.58
     circadian
    1.55
     sleeps
    1.50
     slept
    1.45
     sommeil
    1.44
    Activations Density 0.259%

    No Known Activations