© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130655
    Prev
    Next
    INDEX
    Explanations

    uro followed by medical suffixes

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

    The neuron detects content related to urology or urological medical terms.

    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
     він
    -2.38
     jotka
    -2.36
    s
    -2.34
    廡
    -2.30
     而
    -2.30
    ל
    -2.27
     които
    -2.25
    </h5>
    -2.23
    y
    -2.23
    　　*
    -2.19
    POSITIVE LOGITS
     Other
    2.83
     Partly
    2.34
     Placing
    2.34
     Pushing
    2.27
    鏟
    2.23
     Exciting
    2.22
     Advantages
    2.20
     Finding
    2.16
     Removing
    2.13
     OTHER
    2.11
    Activations Density 0.027%

    No Known Activations