© 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. 34-GEMMASCOPE-RES-131K
    7. 98812
    Prev
    Next
    INDEX
    Explanations

    radiographs and X-rays

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

    medical imaging terminology, particularly related to radiography and X-ray 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
     algae
    -0.78
    ropol
    -0.78
    Ŏ
    -0.77
     Refunds
    -0.74
    仿
    -0.73
    🅒
    -0.73
    ൻ
    -0.73
    ฬ
    -0.73
    mple
    -0.71
    WebKit
    -0.70
    POSITIVE LOGITS
     X
    2.25
     x
    1.95
     radio
    1.81
    レント
    1.52
     radiology
    1.52
    radio
    1.43
    X
    1.34
     Röntgen
    1.27
     rö
    1.25
    getX
    1.25
    Activations Density 0.145%

    No Known Activations