© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45150
    Prev
    Next
    INDEX
    Explanations

    medicaid, medicare, and healthcare services

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

    references to Medicaid and related healthcare programs.

    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
    榈
    -2.30
    бирать
    -2.20
     soothe
    -2.09
    喾
    -2.09
     Gegenstände
    -2.08
    готовления
    -2.08
    餮
    -2.08
    僦
    -2.08
    AddHtmlAttribute
    -2.05
     instala
    -2.05
    POSITIVE LOGITS
    {
    2.58
    C
    2.34
    ؟
    2.33
    by
    2.30
    www
    2.25
    where
    2.20
    e
    2.19
    薆
    2.14
    ？”
    2.13
     wszystkie
    2.13
    Activations Density 0.003%

    No Known Activations