© 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. 34-GEMMASCOPE-RES-131K
    7. 92509
    Prev
    Next
    INDEX
    Explanations

    test or variations thereof

    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
     должен
    -0.75
    ERY
    -0.74
    Women
    -0.71
    ₫
    -0.69
    ⮕
    -0.68
    mings
    -0.67
    女人
    -0.67
     vulnerable
    -0.66
     tric
    -0.66
    Woman
    -0.66
    POSITIVE LOGITS
    testa
    0.96
    吒
    0.85
    getTest
    0.84
     resultar
    0.82
     potr
    0.79
     Tester
    0.77
    UDO
    0.77
     Cosby
    0.76
     grueso
    0.76
     اجتما
    0.76
    Activations Density 0.025%

    No Known Activations