© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1607
    Prev
    Next
    INDEX
    Explanations

    socioeconomic inequality and poverty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_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
     Cretaceous
    1.07
     увлека
    0.96
    varlak
    0.95
     elegante
    0.95
    驸
    0.95
     divertida
    0.94
     Memories
    0.94
    🦖
    0.93
     conjugates
    0.93
     masti
    0.92
    POSITIVE LOGITS
     poverty
    3.22
     Poverty
    3.01
     pobreza
    2.81
     homeless
    2.81
     homelessness
    2.79
     Homeless
    2.70
     unemployment
    2.69
    overty
    2.63
    貧
    2.56
     unemployed
    2.56
    Activations Density 1.345%

    No Known Activations