© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10743
    Prev
    Next
    INDEX
    Explanations

    sleep is

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

    The neuron spikes on tokens referring to sleep and nighttime (e.g. “sleep,” “night,” “bed,” “hour,” “daylight”).

    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
    
    0.78
     artisanal
    0.75
     multinationals
    0.75
     Control
    0.73
     linestyle
    0.73
    堰
    0.73
     Reef
    0.72
     Value
    0.72
     archipelago
    0.72
    芒
    0.72
    POSITIVE LOGITS
    Night
    2.05
     dormir
    1.97
    💤
    1.95
     slept
    1.93
    夜
    1.91
     sleep
    1.86
    😴
    1.85
    sleeping
    1.83
    睡眠
    1.81
    睡觉
    1.81
    Activations Density 1.153%

    No Known Activations