© 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. 12695
    Prev
    Next
    INDEX
    Explanations

    sleep and sleep hygiene

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

    The neuron strongly activates on mentions of sleeping—any form of the word “sleep” (and closely related sleep contexts like “slept,” “bed,” or “wake up” in relation to sleep).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "sleep" and related sleep-related terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of sleep and closely related states, actions, or routines (e.g., sleeping, waking, bedtime, rest, dreams, night).

    oai_token-act-pair · gpt-5Triggered 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
     Tril
    0.63
    chik
    0.62
    高兴
    0.60
    ದೇ
    0.60
    灵
    0.60
    躬
    0.59
    튕
    0.59
    не
    0.59
    morrow
    0.59
    রি
    0.59
    POSITIVE LOGITS
    💤
    0.86
     ngủ
    0.69
     tidur
    0.65
     slee
    0.64
     SLE
    0.61
    slee
    0.61
    SLE
    0.61
    😴
    0.61
     Slee
    0.58
    Sleeping
    0.58
    Activations Density 0.113%

    No Known Activations