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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83350
    Prev
    Next
    INDEX
    Explanations

    patient privacy and HIPAA

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

    content related to privacy, confidentiality, and legal protections of information.

    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
     littérature
    -0.74
     ście
    -0.73
    وبر
    -0.72
     tenere
    -0.72
     Opfer
    -0.71
    femin
    -0.70
    ільки
    -0.69
    Hora
    -0.69
     chemist
    -0.69
    olem
    -0.68
    POSITIVE LOGITS
     PHI
    1.46
     patient
    1.33
    PHI
    1.31
     Patient
    1.24
    患者
    1.17
     patients
    1.12
    patient
    1.11
    Patient
    1.10
     Patients
    1.06
     HIPAA
    1.05
    Activations Density 0.017%

    No Known Activations