© 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. 10268
    Prev
    Next
    INDEX
    Explanations

    basic living conditions and poverty

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

    poverty and hardship

    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
    ोजित
    0.50
     millennials
    0.48
     appointees
    0.48
    利率
    0.47
    िएट
    0.46
    congress
    0.46
     investors
    0.46
    骜
    0.45
     turbocharged
    0.45
     campaigned
    0.44
    POSITIVE LOGITS
     kerosene
    0.70
     subsistence
    0.68
     गरीबी
    0.68
     cocinar
    0.68
     cooking
    0.64
     poverty
    0.64
     comida
    0.64
     pobreza
    0.64
     rations
    0.61
     দরিদ্র
    0.61
    Activations Density 0.145%

    No Known Activations