© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77394
    Prev
    Next
    INDEX
    Explanations

    testing or test behavior

    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
     gyóg
    -1.16
     sár
    -0.93
    ilane
    -0.87
     fermés
    -0.87
     színes
    -0.86
     lány
    -0.85
     bőr
    -0.85
    asiswa
    -0.81
     ouverts
    -0.77
     csomag
    -0.77
    POSITIVE LOGITS
     testing
    7.34
     test
    7.06
     tested
    6.16
     tests
    5.94
     Testing
    5.66
    测试
    5.66
    testing
    5.34
    Testing
    5.31
    test
    5.03
     Test
    4.91
    Activations Density 0.407%

    No Known Activations