© 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. 10-GEMMASCOPE-RES-131K
    7. 127569
    Prev
    Next
    INDEX
    Explanations

    Chronic obstructive pulmonary disease

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

    medical terms and abbreviations related to chronic obstructive pulmonary disease (COPD).

    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
    Aside
    -1.78
    してみた
    -1.67
     這
    -1.63
     digitized
    -1.61
    That
    -1.55
     When
    -1.52
    謨
    -1.52
    時には
    -1.51
    ليات
    -1.51
     That
    -1.51
    POSITIVE LOGITS
    2
    1.82
     />
    1.73
     để
    1.67
     of
    1.60
    艄
    1.58
     anything
    1.55
     &
    1.54
    0
    1.48
     мар
    1.44
    XCTAssertEqual
    1.44
    Activations Density 0.064%

    No Known Activations