© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44825
    Prev
    Next
    INDEX
    Explanations

    ethnicity and race, varied contexts

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

    The neuron strongly activates on occurrences of the word “ethnicity” or other “ethnic” references in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    It
    -2.67
    因
    -2.66
    There
    -2.61
     отличается
    -2.59
    或
    -2.53
    颜色
    -2.52
     définiti
    -2.52
    杁
    -2.47
    When
    -2.34
    を
    -2.34
    POSITIVE LOGITS
    
    2.75
    同士
    2.72
     procurando
    2.53
    谖
    2.52
    
    2.50
    BUT
    2.41
    
    2.31
    焄
    2.30
    蛱
    2.28
     serão
    2.27
    Activations Density 0.004%

    No Known Activations