© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56946
    Prev
    Next
    INDEX
    Explanations

    social welfare programs

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

    The neuron fires on mentions of health‐care coverage or social health protection schemes (e.g. UHC, Medicare, income security in ill health).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    艏
    -0.81
    management
    -0.79
    asses
    -0.79
    laire
    -0.79
    latLng
    -0.78
    指示
    -0.76
     subserv
    -0.75
     jat
    -0.75
    |.
    -0.75
    ENARIO
    -0.74
    POSITIVE LOGITS
     social
    1.68
     welfare
    1.55
     Social
    1.52
     universal
    1.50
    Social
    1.40
     programs
    1.33
     insurance
    1.25
    social
    1.22
     Welfare
    1.20
    Welfare
    1.17
    Activations Density 0.034%

    No Known Activations