Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8531
    Prev
    Next
    INDEX
    Explanations

    types of medical tests

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

    terms related to medical tests and examinations.

    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
     minhas
    -0.91
     növény
    -0.79
     Gegner
    -0.77
     condomínio
    -0.76
    ristol
    -0.75
    inematics
    -0.75
     gdyż
    -0.75
    čená
    -0.75
     Produits
    -0.75
     Investigator
    -0.74
    POSITIVE LOGITS
     tests
    5.44
     testing
    4.47
     test
    4.47
     Tests
    3.66
    tests
    3.66
    Tests
    3.41
    测试
    3.33
     TESTS
    3.11
    テスト
    3.08
    TESTS
    2.92
    Activations Density 0.199%

    No Known Activations