© 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. 195360
    Prev
    Next
    INDEX
    Explanations

    social security benefits and qualification

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

    Social Security and benefits

    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
     Sở
    0.43
     ОК
    0.43
    норийска
    0.43
     Offenders
    0.42
    鸬
    0.42
    冠军
    0.42
     اوكي
    0.42
     বিমানবন্দ
    0.42
    蜂蜜
    0.41
    噘
    0.40
    POSITIVE LOGITS
     worker
    0.45
     employer
    0.45
     tick
    0.44
    worker
    0.44
     Bandit
    0.43
     SSA
    0.43
     playwright
    0.42
    tick
    0.42
    employer
    0.41
     miner
    0.41
    Activations Density 0.056%

    No Known Activations