© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62426
    Prev
    Next
    INDEX
    Explanations

    bedtime sleep

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

    This neuron detects explicit mentions of scheduled times and routine time expressions—especially around bedtime or nightly activities.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    hello
    -0.81
    Lunch
    -0.81
    Urban
    -0.79
    देश
    -0.79
    روز
    -0.79
    yaç
    -0.77
     Fils
    -0.76
    SARS
    -0.73
    duration
    -0.73
    dauer
    -0.73
    POSITIVE LOGITS
     bedtime
    3.47
     bed
    2.73
     sleep
    2.39
    Goodnight
    2.27
     sleeping
    2.08
     asleep
    1.94
     Bed
    1.90
    sleep
    1.90
    bed
    1.89
     dormir
    1.88
    Activations Density 0.027%

    No Known Activations