© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60647
    Prev
    Next
    INDEX
    Explanations

    Black and African identity

    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
    Everyone
    -1.02
     кото
    -0.93
    其中的
    -0.91
     lema
    -0.90
    everyone
    -0.89
    odyne
    -0.89
     アウター
    -0.87
     Everyone
    -0.87
    onSelect
    -0.85
     devout
    -0.84
    POSITIVE LOGITS
     Black
    1.37
     America
    1.29
     black
    1.20
    Black
    1.15
     African
    1.13
     سیاه
    1.09
    zegovina
    1.08
     our
    1.02
    America
    1.00
    African
    0.98
    Activations Density 0.035%

    No Known Activations