© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21009
    Prev
    Next
    INDEX
    Explanations

    developing vs. developed nations, wealth, poverty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     samh
    0.45
     ustawy
    0.44
    ㎠
    0.43
     جامعه
    0.42
     مسجد
    0.42
     აღმასრულებელი
    0.42
     المجتمع
    0.41
    マンション
    0.41
    愪
    0.41
     statewide
    0.41
    POSITIVE LOGITS
     poorest
    0.83
     poverty
    0.79
     poorer
    0.79
     wealthier
    0.77
     aid
    0.75
     pobreza
    0.74
    援助
    0.70
     impoverished
    0.70
     unfair
    0.69
     richer
    0.68
    Activations Density 0.007%

    No Known Activations