© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14187
    Prev
    Next
    INDEX
    Explanations

    poverty

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

    socialist, meritocracy, inequality

    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_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
     paix
    0.53
     activités
    0.50
     responsáveis
    0.50
     effectué
    0.49
     Nauka
    0.46
     rivers
    0.45
    膂
    0.45
     asteroids
    0.44
    ▥
    0.44
     calmer
    0.43
    POSITIVE LOGITS
     poverty
    1.48
    貧
    1.40
     गरीबी
    1.37
     Poverty
    1.30
     দারিদ্র
    1.25
    贫
    1.24
     pobreza
    1.20
     गरीब
    1.15
     দরিদ্র
    1.15
     poorest
    1.12
    Activations Density 0.270%

    No Known Activations