© 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. 10-GEMMASCOPE-RES-131K
    7. 72482
    Prev
    Next
    INDEX
    Explanations

    medical ultrasound imaging

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

    medical imaging terminology, particularly related to ultrasound/sonography.

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

    The neuron strongly activates on tokens that compose “ultrasound” or “ultrasonography,” so it’s detecting mentions of ultrasound imaging.

    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
    тное
    -1.57
    ڳ
    -1.38
    izoen
    -1.38
    ⡃
    -1.33
     vektör
    -1.30
    ”،
    -1.30
    駙
    -1.30
     which
    -1.29
    händler
    -1.27
     renforcé
    -1.26
    POSITIVE LOGITS
    {
    1.62
    то
    1.55
     korzyst
    1.47
    嵓
    1.44
    偁
    1.42
     entire
    1.34
     affaire
    1.31
    
    1.31
    あとは
    1.30
    didSet
    1.30
    Activations Density 0.098%

    No Known Activations