© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102
    Prev
    Next
    INDEX
    Explanations

    subsidies and entitlements

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

    government aid, subsidies, and welfare programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    科学家
    0.53
    丛
    0.50
    艺术
    0.50
    细胞
    0.49
    实验室
    0.49
    实验
    0.49
    绘
    0.48
    侦
    0.48
    呕
    0.48
    绚
    0.48
    POSITIVE LOGITS
     subsidies
    1.08
     subsidy
    1.06
     eligibility
    1.05
     eligible
    0.98
     entitlements
    0.96
     subsid
    0.96
     subsidized
    0.96
     beneficiaries
    0.95
     payments
    0.92
    eligible
    0.86
    Activations Density 0.377%

    No Known Activations