© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 4408
    Prev
    Next
    INDEX
    Explanations

    sleep and winding down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ስቃሴ
    0.49
    Lunch
    0.43
     invoices
    0.38
     invoicing
    0.37
     маркетин
    0.37
     философ
    0.36
     Sentencing
    0.36
    晠
    0.36
    步伐
    0.35
     Lunch
    0.35
    POSITIVE LOGITS
     sleep
    2.77
     Sleep
    2.48
    Sleep
    2.45
     sleeping
    2.42
    睡眠
    2.39
    sleep
    2.34
     slept
    2.28
     sleeps
    2.25
    睡
    2.22
     dormir
    2.14
    Activations Density 0.350%

    No Known Activations