© 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. 68698
    Prev
    Next
    INDEX
    Explanations

    time and timestamps

    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
     to
    0.49
     require
    0.48
    index
    0.48
     ..
    0.47
    >
    0.47
    to
    0.47
     argue
    0.46
     you
    0.46
     opener
    0.46
     requires
    0.46
    POSITIVE LOGITS
    籾
    0.53
    الی
    0.51
    نتی
    0.50
    Timestamp
    0.50
    畯
    0.50
    ArrivalTime
    0.48
    ಾಯ
    0.48
     벨
    0.48
     मुहूर्त
    0.48
    धव
    0.47
    Activations Density 0.001%

    No Known Activations