© 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. 10-GEMMASCOPE-RES-131K
    7. 40986
    Prev
    Next
    INDEX
    Explanations

    osteoarthritis

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

    This neuron detects abbreviations, particularly scientific and medical acronyms, with high activation for terms like "OA" (osteoarthritis), "HOA" (homeowners association), and "PFOA" (perfluorooctanoic acid).

    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_10/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
     colorear
    -2.81
     なら
    -2.77
     defeats
    -2.63
    になりますが
    -2.63
    vantaged
    -2.53
    这般
    -2.28
     そう
    -2.27
     recomendar
    -2.22
     combinar
    -2.22
     destacó
    -2.22
    POSITIVE LOGITS
    '
    3.91
    {
    3.41
    s
    3.28
    AN
    2.61
    AS
    2.50
    D
    2.47
    AT
    2.42
    B
    2.39
    v
    2.34
    --
    2.33
    Activations Density 0.027%

    No Known Activations