© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42432
    Prev
    Next
    INDEX
    Explanations

    medical imaging procedures

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

    This neuron detects medical imaging techniques and procedures, particularly terms ending in "-graphy" like "angiography", "discography", and "sonography".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of medical imaging or interventional procedure names, especially those ending in “‐graphy” or “‐plasty.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Dumnezeu
    -1.37
    Referenties
    -1.25
     there
    -1.22
    甚至
    -1.18
     Majority
    -1.16
    beca
    -1.16
    倫
    -1.14
     протягом
    -1.13
     남자
    -1.13
     Weisheit
    -1.11
    POSITIVE LOGITS
     她
    1.41
    ,"
    1.38
    êque
    1.34
    -------------</
    1.31
    __.__
    1.30
     test
    1.28
    ServiceTest
    1.25
     aktive
    1.24
    __()
    1.18
     arme
    1.17
    Activations Density 0.319%

    No Known Activations