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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44636
    Prev
    Next
    INDEX
    Explanations

    tumor necrosis factor alpha, IL-6

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

    scientific terminology related to interleukins, cytokines, and other molecular factors in immunology research.

    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
     camiset
    -1.66
    牂
    -1.65
     disponibilités
    -1.63
    k
    -1.63
     capucha
    -1.62
    ława
    -1.60
     étan
    -1.60
    "-
    -1.59
     fixé
    -1.57
     bouteilles
    -1.57
    POSITIVE LOGITS
     and
    2.67
     to
    2.19
     by
    1.81
    ↵↵
    1.60
     from
    1.53
     which
    1.52
     or
    1.47
    .
    1.47
     lacking
    1.41
    良いです
    1.39
    Activations Density 0.195%

    No Known Activations