© 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. 48124
    Prev
    Next
    INDEX
    Explanations

    Medicaid programs and services

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    **********/
    -0.88
     Argentino
    -0.86
     Ró
    -0.80
     Lokal
    -0.79
     cristianos
    -0.79
     FACILITIES
    -0.78
    גרפיה
    -0.78
     précé
    -0.78
    ITIC
    -0.78
    FLO
    -0.77
    POSITIVE LOGITS
     Medicaid
    1.43
     state
    1.07
     provider
    1.05
     State
    1.03
     children
    1.02
    Medica
    0.94
     Recipient
    0.81
    State
    0.81
     recipient
    0.81
     providers
    0.79
    Activations Density 0.025%

    No Known Activations