© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79359
    Prev
    Next
    INDEX
    Explanations

    survival analysis

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

    statistical analysis terminology related to Cox proportional hazard regression models in medical research studies.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    額
    -0.74
     Sada
    -0.73
    prf
    -0.71
    ㄱ
    -0.69
     Houghton
    -0.69
     disordered
    -0.69
    пода
    -0.69
     シャツ
    -0.68
     твори
    -0.68
    entid
    -0.68
    POSITIVE LOGITS
     survival
    2.72
     hazard
    2.66
     Kaplan
    2.64
     Survival
    2.44
    Survival
    2.42
     Hazard
    2.34
    hazard
    2.17
    survival
    2.14
    Hazard
    2.09
     Cox
    2.08
    Activations Density 0.210%

    No Known Activations