© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9557
    Prev
    Next
    INDEX
    Explanations

    unix timestamp

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

    Unix 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_40_width_16k_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
     週
    0.38
     ribs
    0.38
    ალ
    0.38
    rays
    0.38
    Years
    0.37
    ød
    0.37
    荤
    0.37
    oday
    0.36
    觥
    0.36
    每周
    0.36
    POSITIVE LOGITS
     unix
    1.05
     timestamp
    1.03
    timestamp
    1.02
    unix
    0.97
     UNIX
    0.96
    currentTime
    0.95
     timestamps
    0.93
     Unix
    0.93
     Timestamp
    0.92
    TIMESTAMP
    0.91
    Activations Density 0.024%

    No Known Activations