© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49261
    Prev
    Next
    INDEX
    Explanations

    health and human services

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

    references to government health organizations such as the Department of Health and Human Services, Centers for Medicare and Medicaid Services, and related agencies.

    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
     gine
    -0.85
     Miko
    -0.84
    Gbps
    -0.81
     filmo
    -0.81
     malla
    -0.81
    ⚗
    -0.81
    Minerals
    -0.79
     Mundo
    -0.78
     nori
    -0.78
     vetro
    -0.77
    POSITIVE LOGITS
     CMS
    2.88
    CMS
    2.67
    cms
    2.05
     cms
    1.89
     Medicare
    1.71
     Centers
    1.60
    Cms
    1.53
    Medicare
    1.48
     HHS
    1.34
    Centers
    1.22
    Activations Density 0.060%

    No Known Activations