© 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. 34-GEMMASCOPE-RES-131K
    7. 3215
    Prev
    Next
    INDEX
    Explanations

    Affordable Care Act

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

    words and phrases related to the Affordable Care Act (Obamacare) and healthcare policy.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is tuned to spotting mentions of Obamacare and related Affordable Care Act health-insurance terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    dass
    -1.00
     フライ
    -0.90
    Newspaper
    -0.85
    ujete
    -0.83
    Gandhi
    -0.81
     Бог
    -0.81
     elevador
    -0.79
    Chand
    -0.78
    lardır
    -0.78
    Plasma
    -0.78
    POSITIVE LOGITS
     Affordable
    3.86
     ACA
    2.91
    Affordable
    2.72
     Obamacare
    2.50
    ACA
    2.31
     affordable
    2.02
     Patient
    1.98
     healthcare
    1.74
    affordable
    1.67
    aca
    1.60
    Activations Density 0.057%

    No Known Activations