© 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. 34-GEMMASCOPE-RES-131K
    7. 77772
    Prev
    Next
    INDEX
    Explanations

    renal function and GFR

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

    medical and technical terms related to kidney function and renal measurements.

    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
    <<"\
    -0.81
     تعالى
    -0.75
     ನ
    -0.73
     гита
    -0.71
    ỉ
    -0.70
     Compressor
    -0.70
    álló
    -0.69
    трите
    -0.69
     Guitar
    -0.68
     copper
    -0.68
    POSITIVE LOGITS
     kidneys
    1.68
     kidney
    1.66
     renal
    1.60
     creatinine
    1.52
     filtration
    1.49
    GFR
    1.43
     glomer
    1.42
     Kidney
    1.38
    腎
    1.33
    renal
    1.32
    Activations Density 0.114%

    No Known Activations