© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5698
    Prev
    Next
    INDEX
    Explanations

    black american people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     Tolkien
    0.78
     blonde
    0.75
    鞑
    0.74
    blonde
    0.72
     Norweg
    0.70
     blond
    0.68
    鸢
    0.67
     austri
    0.65
     Zden
    0.64
     Australien
    0.63
    POSITIVE LOGITS
    🏾
    1.74
     African
    1.72
    African
    1.56
     Afro
    1.55
     NAACP
    1.54
     Harlem
    1.48
     afro
    1.43
    🏿
    1.42
    african
    1.34
    非洲
    1.34
    Activations Density 0.271%

    No Known Activations