© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49747
    Prev
    Next
    INDEX
    Explanations

    ethnic 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
    دهی
    -0.97
    GNUC
    -0.90
    ון
    -0.87
     саме
    -0.84
     exponent
    -0.82
     protease
    -0.82
     ACO
    -0.77
     regimens
    -0.76
    ema
    -0.74
    たつ
    -0.74
    POSITIVE LOGITS
    ities
    1.31
     group
    1.22
     minority
    1.20
     minorities
    1.12
     groups
    1.09
     cleansing
    1.05
     background
    1.01
    ită
    0.95
    group
    0.90
     origin
    0.89
    Activations Density 0.019%

    No Known Activations