© 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. 53-GEMMASCOPE-2-RES-262K
    7. 37485
    Prev
    Next
    INDEX
    Explanations

    associating Hispanic and other race categories

    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_53_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
     black
    1.38
    black
    1.29
    BLACK
    1.25
    黑色
    1.20
     BLACK
    1.18
    黑
    1.18
    Black
    1.15
     블랙
    1.11
    黒
    1.11
     blacks
    1.09
    POSITIVE LOGITS
     Hispanic
    1.16
     hispanic
    1.07
     Hispanics
    1.01
     Latino
    0.95
    Hispanic
    0.94
     Latinos
    0.90
     latino
    0.88
     Mexican
    0.73
     Puerto
    0.65
     испан
    0.64
    Activations Density 0.013%

    No Known Activations