© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 63616
    Prev
    Next
    INDEX
    Explanations

    medical professions and health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    坟
    0.45
    错了
    0.42
    {[\
    0.39
    instructions
    0.39
    Instructions
    0.38
     detalhes
    0.38
    criptive
    0.37
    墳
    0.36
    STRUCTIONS
    0.36
     detalles
    0.36
    POSITIVE LOGITS
     medical
    1.11
     infirm
    1.11
     medics
    0.98
     health
    0.97
     medic
    0.95
    medical
    0.95
     nurse
    0.94
     Medical
    0.94
     medizin
    0.93
     Infirm
    0.92
    Activations Density 0.002%

    No Known Activations