© 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. 34-GEMMASCOPE-RES-131K
    7. 77984
    Prev
    Next
    INDEX
    Explanations

    medical events and follow-up periods

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

    medical research text and clinical study reports from academic medical journals.

    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_34/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
     microbiome
    -1.58
     zebrafish
    -1.21
    都沒
    -1.20
    哪裡
    -1.16
     qPCR
    -1.14
     scaffolds
    -1.07
     онлайн
    -1.05
     implementación
    -1.05
     arXiv
    -1.05
     blogger
    -1.02
    POSITIVE LOGITS
     läßt
    1.19
     markedly
    1.14
     Polaroid
    1.10
    #{
    0.97
     enfermo
    0.97
    下さい
    0.96
     emphasizing
    0.94
     emphasizes
    0.94
     caos
    0.93
     matang
    0.93
    Activations Density 3.674%

    No Known Activations