© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13541
    Prev
    Next
    INDEX
    Explanations

    nursing and patient care

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

    patient care and health services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    医生
    0.48
    医師
    0.48
     চিকিৎসক
    0.47
     चिकित्सक
    0.46
     Thyroid
    0.46
     lekar
    0.44
     utterances
    0.44
    ):["
    0.43
    ప్తి
    0.42
     Ärz
    0.41
    POSITIVE LOGITS
     home
    0.49
     домой
    0.49
    家に
    0.49
    HOME
    0.48
    Admission
    0.48
    Cases
    0.48
    care
    0.47
     care
    0.47
    home
    0.47
    Chronic
    0.47
    Activations Density 0.233%

    No Known Activations