© 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. 53-GEMMASCOPE-2-RES-65K
    7. 16822
    Prev
    Next
    INDEX
    Explanations

    timing for actions

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

    peak and off-peak times

    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_53_width_65k_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
    last
    0.39
    的基础上
    0.39
    guesses
    0.39
    这场
    0.39
    ej
    0.37
    reira
    0.36
    下一步
    0.36
    磕
    0.35
    Celebr
    0.35
    作用
    0.35
    POSITIVE LOGITS
     odd
    0.84
     daytime
    0.84
     anytime
    0.77
     mornings
    0.74
    いつでも
    0.73
     evenings
    0.73
     convenient
    0.73
     nighttime
    0.71
     Anytime
    0.71
     ciertas
    0.68
    Activations Density 0.074%

    No Known Activations