© 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. 34-GEMMASCOPE-RES-131K
    7. 62872
    Prev
    Next
    INDEX
    Explanations

    testing and variants

    np_acts-logits-general · gemini-2.5-flash-lite

    legal and technical document numerical values including section numbers, time periods, and measurements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    propag
    -0.79
    aleg
    -0.79
    Tors
    -0.74
    ствие
    -0.72
     Saty
    -0.72
     Yearbook
    -0.72
     pulsera
    -0.72
     LGBT
    -0.71
     counter
    -0.71
     homo
    -0.70
    POSITIVE LOGITS
     testing
    1.47
     test
    1.44
    测试
    1.07
     Testing
    1.06
     Test
    1.06
     испыта
    1.00
     tested
    0.98
    ptest
    0.97
     probar
    0.96
    Test
    0.94
    Activations Density 0.001%

    No Known Activations