© 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. 119122
    Prev
    Next
    INDEX
    Explanations

    medical contrast agents

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

    medical imaging contrast agents and radiographic terminology.

    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
     cryo
    -0.74
     편
    -0.74
     ADS
    -0.73
    AGAT
    -0.73
    ühungen
    -0.72
     sabre
    -0.70
     exud
    -0.69
    ब्द
    -0.69
    reflection
    -0.69
     DHT
    -0.68
    POSITIVE LOGITS
     contrast
    3.34
    Contrast
    2.80
    contrast
    2.73
     Contrast
    2.64
     contraste
    2.20
     contrasts
    2.16
     контра
    1.98
     contrasted
    1.66
     dye
    1.65
     contrasting
    1.64
    Activations Density 0.204%

    No Known Activations