© 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. 78538
    Prev
    Next
    INDEX
    Explanations

    diseases and conditions

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

    medical conditions listed in a series separated by commas.

    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
     cardiovascular
    -1.27
     Cardiology
    -1.26
     Cardiovascular
    -1.17
    心跳
    -0.93
     Cardiac
    -0.92
     heartbroken
    -0.92
     heartbreak
    -0.92
    心脏
    -0.91
     Hartmann
    -0.90
     cardiac
    -0.88
    POSITIVE LOGITS
     lungs
    0.80
     strokes
    0.75
     stroke
    0.75
     stomach
    0.75
     kidneys
    0.73
     Wellington
    0.72
    Wellington
    0.72
     İ
    0.72
     minds
    0.71
    seit
    0.70
    Activations Density 0.056%

    No Known Activations