© 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. 3439
    Prev
    Next
    INDEX
    Explanations

    philosophy of medicine, art, science

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

    references to "philosophy of" followed by a subject or discipline.

    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
     leaving
    -0.90
    úncia
    -0.73
     lucy
    -0.70
     вос
    -0.69
    putstr
    -0.68
    相机
    -0.68
     chassis
    -0.67
     つの
    -0.66
     RAI
    -0.66
    CAF
    -0.66
    POSITIVE LOGITS
    blos
    0.71
     afectadas
    0.65
     ව
    0.65
    Pham
    0.65
    christian
    0.65
     Webber
    0.64
    vlo
    0.64
     sytu
    0.64
    Hb
    0.63
    (("
    0.63
    Activations Density 0.058%

    No Known Activations