© 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. 22-GEMMASCOPE-RES-131K
    7. 16494
    Prev
    Next
    INDEX
    Explanations

    lymphovascular space involvement

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

    medical and scientific terminology related to cell biology and medical treatments.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵
    -0.98
     during
    -0.97
     when
    -0.95
     by
    -0.94
     provides
    -0.91
    ">'.$
    -0.90
     strengthen
    -0.90
     find
    -0.85
     where
    -0.84
    enegger
    -0.83
    POSITIVE LOGITS
     позволя
    0.97
    ୂ
    0.91
    샐
    0.90
     tournoi
    0.89
    neté
    0.85
     Duitse
    0.85
    அ
    0.84
    缃
    0.84
     afbeelding
    0.84
    өздер
    0.84
    Activations Density 0.730%

    No Known Activations