© 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. 128710
    Prev
    Next
    INDEX
    Explanations

    test structures, models, trials

    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
    下意识
    -1.23
    唠
    -1.16
     السياس
    -1.03
     ویتامین
    -1.02
     fantástico
    -1.01
    方才
    -1.00
    нави
    -0.98
    🩻
    -0.97
     riego
    -0.96
    利润
    -0.93
    POSITIVE LOGITS
     test
    2.66
     testing
    2.39
     tests
    1.82
    test
    1.44
     tester
    1.42
    测试
    1.41
     Test
    1.38
    getTest
    1.32
     sample
    1.29
     demonstration
    1.27
    Activations Density 0.129%

    No Known Activations