© 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. 34-GEMMASCOPE-RES-131K
    7. 31397
    Prev
    Next
    INDEX
    Explanations

    ethnic and religious minorities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Neale
    -0.78
    xel
    -0.77
    annes
    -0.76
    𝘪
    -0.74
    訟
    -0.73
     Merle
    -0.71
    lars
    -0.68
    DIVISION
    -0.68
     isoto
    -0.68
     }>
    -0.67
    POSITIVE LOGITS
     minority
    3.09
     minorities
    2.83
     Minority
    1.84
     groups
    1.59
     MINOR
    1.45
     мень
    1.42
    少数
    1.38
     minori
    1.30
    minor
    1.28
    groups
    1.27
    Activations Density 0.027%

    No Known Activations