© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19563
    Prev
    Next
    INDEX
    Explanations

    specific dates and times

    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_10/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
    ೣ
    -2.08
     first
    -1.99
     renowned
    -1.96
     нескольких
    -1.95
    ᛬
    -1.93
     opulent
    -1.88
     differing
    -1.86
    terdam
    -1.84
     réserve
    -1.83
    我现在
    -1.83
    POSITIVE LOGITS
     This
    2.38
    $
    1.90
    这个
    1.86
     would
    1.72
     devise
    1.70
    ꔛ
    1.64
     professionelle
    1.63
     if
    1.62
    這個
    1.61
     هذا
    1.56
    Activations Density 0.018%

    No Known Activations