© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106613
    Prev
    Next
    INDEX
    Explanations

    Unix epoch time

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ध्यम
    -0.82
    片
    -0.79
     ポン
    -0.78
    cdonald
    -0.75
     preescolar
    -0.73
     liệt
    -0.70
    勤務
    -0.69
    ēd
    -0.69
    hoku
    -0.69
     shoot
    -0.69
    POSITIVE LOGITS
     Unix
    2.38
     unix
    2.22
     UNIX
    2.11
    unix
    1.93
    Unix
    1.91
     epoch
    1.82
    UNIX
    1.79
     timestamp
    1.79
    epoch
    1.66
     Epoch
    1.59
    Activations Density 0.062%

    No Known Activations