© 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. 106406
    Prev
    Next
    INDEX
    Explanations

    survival outcomes

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

    phrases related to survival rates and outcomes in medical research papers, particularly focusing on cancer and disease prognosis statistics.

    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
    imte
    -0.78
     Daily
    -0.75
    )});
    -0.75
    lidae
    -0.74
    pland
    -0.74
    eezy
    -0.74
    ⊷
    -0.72
    了出去
    -0.71
    lids
    -0.71
     quotidienne
    -0.71
    POSITIVE LOGITS
     survival
    3.30
     Survival
    2.58
    survival
    2.52
    Survival
    2.50
     SURV
    1.77
     survi
    1.75
     survive
    1.66
     supervivencia
    1.63
    生存
    1.61
     outcomes
    1.60
    Activations Density 0.314%

    No Known Activations