© 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. 91517
    Prev
    Next
    INDEX
    Explanations

    social assistance programs and benefits

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

    The neuron activates on mentions of government social‐welfare or assistance programs (e.g. welfare, human services, food‐stamp, social‐assistance programs).

    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
     Pach
    -0.84
     öffnen
    -0.77
    ハンドル
    -0.75
    Спасылкі
    -0.74
     Sext
    -0.73
    urich
    -0.71
     відкри
    -0.71
    鈞
    -0.71
    olalar
    -0.71
     stør
    -0.70
    POSITIVE LOGITS
     welfare
    1.77
     Welfare
    1.55
     recipients
    1.44
    welfare
    1.44
    Welfare
    1.43
     Work
    1.23
     recipient
    1.17
    Work
    1.05
    Recipients
    1.03
     TAN
    1.02
    Activations Density 0.022%

    No Known Activations