© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16328
    Prev
    Next
    INDEX
    Explanations

    sleep and related states

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

    sleep and rest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    arı
    0.57
    anın
    0.56
    ación
    0.55
    ется
    0.52
    ución
    0.51
    '')
    0.51
    વા
    0.48
    🚪
    0.48
    outputs
    0.48
    nement
    0.48
    POSITIVE LOGITS
     sleeping
    0.91
     Sleeping
    0.91
    Sleeping
    0.79
     sleeps
    0.79
     dormir
    0.77
    sleeping
    0.77
     tidur
    0.73
    SLE
    0.73
     slept
    0.71
     slumber
    0.71
    Activations Density 0.232%

    No Known Activations