© 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. 79340
    Prev
    Next
    INDEX
    Explanations

    medical and research fields

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

    references to clinical, medical, or scientific journals and publications.

    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
     socket
    -0.81
     working
    -0.78
     Persön
    -0.66
     error
    -0.65
     сту
    -0.64
    大帝
    -0.63
    sila
    -0.63
    ごとに
    -0.62
     liên
    -0.62
     transferencia
    -0.62
    POSITIVE LOGITS
     Hej
    0.77
    Sampling
    0.74
    clf
    0.72
    Chlor
    0.71
     Laurel
    0.69
     dialogues
    0.69
     werfen
    0.68
    Parallel
    0.68
    dab
    0.68
     Confucius
    0.68
    Activations Density 0.048%

    No Known Activations