© 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. 22-GEMMASCOPE-RES-131K
    7. 64808
    Prev
    Next
    INDEX
    Explanations

    days of the week or weekly periods

    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_22/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
     angepasst
    -0.96
    もうすぐ
    -0.94
    igkeit
    -0.93
    ikis
    -0.93
     Tahun
    -0.90
     [''],
    -0.89
     indepen
    -0.86
    IONE
    -0.86
    vénients
    -0.85
     پنجم
    -0.85
    POSITIVE LOGITS
     weekly
    2.66
    weekly
    2.13
     Weekly
    1.95
     week
    1.91
    Weekly
    1.86
     monthly
    1.70
     WEEKLY
    1.62
     semanal
    1.55
     Sunday
    1.45
    week
    1.45
    Activations Density 0.087%

    No Known Activations