© 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. 10-GEMMASCOPE-RES-131K
    7. 127619
    Prev
    Next
    INDEX
    Explanations

    being hospitalized

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

    medical terms related to hospitalization and patient care.

    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
     —
    -1.91
     unearth
    -1.90
    satunya
    -1.78
    感应
    -1.77
     面包
    -1.77
    辂
    -1.71
     transformar
    -1.71
    стрый
    -1.66
    忖
    -1.66
     of
    -1.63
    POSITIVE LOGITS
    7
    2.33
    9
    2.30
    8
    2.22
    許多
    1.95
    5
    1.94
    3
    1.93
    我們
    1.88
    킁
    1.82
    ꜆
    1.81
    6
    1.75
    Activations Density 0.025%

    No Known Activations