© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104705
    Prev
    Next
    INDEX
    Explanations

    development of adverse outcomes

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

    the phrase "the development of" when discussing medical conditions, disease progression, or biological processes.

    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_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
     ENH
    -1.72
    for
    -1.71
    YYY
    -1.69
    再也
    -1.67
     pérd
    -1.66
    ⏑
    -1.64
    than
    -1.64
     substan
    -1.63
    cking
    -1.63
     evoc
    -1.61
    POSITIVE LOGITS
     any
    2.14
     one
    2.05
     during
    2.00
     Some
    1.92
     or
    1.91
     Perhaps
    1.90
     Several
    1.81
     With
    1.77
     What
    1.73
    或
    1.72
    Activations Density 0.145%

    No Known Activations