© 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. 10-GEMMASCOPE-RES-131K
    7. 72476
    Prev
    Next
    INDEX
    Explanations

    Cox proportional hazard regression

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

    statistical analysis methods in medical research, particularly Cox proportional hazard models and Kaplan-Meier survival analysis.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on mentions of statistical modeling and survival‐analysis terminology—especially references to Cox proportional-hazards regression, hazard/risk estimates, and related prognostic or mortality analyses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     znajdu
    -1.65
     what
    -1.63
    alit
    -1.55
    ↵↵
    -1.38
     zaś
    -1.30
    logies
    -1.29
     strongest
    -1.28
    ↵
    -1.28
    contro
    -1.27
     otwor
    -1.27
    POSITIVE LOGITS
     grecque
    1.44
     guir
    1.41
     of
    1.32
    ถ้า
    1.30
     巧克力
    1.27
    getMock
    1.27
     essentielles
    1.26
     tré
    1.25
     Perſ
    1.25
    紲
    1.24
    Activations Density 0.121%

    No Known Activations