© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41550
    Prev
    Next
    INDEX
    Explanations

    work hours and travel

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

    shift work, weekends, holidays

    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_262k_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
     newList
    0.47
     four
    0.45
     fleet
    0.43
     নূতন
    0.41
     daily
    0.41
     new
    0.40
     pipe
    0.40
    烨
    0.40
     Joe
    0.39
     checks
    0.39
    POSITIVE LOGITS
    夜
    0.48
     madrugada
    0.45
    arovski
    0.44
     চলচ্চিত্র
    0.44
    深夜
    0.43
    場合がございます
    0.43
     ஏற்பட
    0.42
     ночью
    0.42
    sometimes
    0.42
    ゥム
    0.41
    Activations Density 0.023%

    No Known Activations