© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103799
    Prev
    Next
    INDEX
    Explanations

    over the weekend

    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
     Thursdays
    -1.16
     Tuesdays
    -1.00
     Wednesdays
    -0.94
     Mondays
    -0.92
    setcounter
    -0.86
    Wednesday
    -0.85
     WEDNESDAY
    -0.80
     thursday
    -0.79
    مق
    -0.77
    वर
    -0.76
    POSITIVE LOGITS
     weekend
    3.81
    weekend
    2.52
     weekends
    2.36
    Weekend
    2.33
     Weekend
    2.17
     WEEKEND
    2.06
    周末
    1.90
     Wochenende
    1.81
    週末
    1.55
     Weeknd
    1.16
    Activations Density 0.031%

    No Known Activations