© 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. 84883
    Prev
    Next
    INDEX
    Explanations

    offensive racial slurs

    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
    rófono
    -0.89
    ಖ
    -0.80
    áng
    -0.76
     bello
    -0.73
     significato
    -0.73
     fals
    -0.72
    讶
    -0.72
    abetes
    -0.71
    Через
    -0.71
    较大
    -0.71
    POSITIVE LOGITS
     Sambo
    1.19
     Nig
    1.13
    Nig
    1.13
     Negro
    1.13
     nigger
    1.11
     slave
    1.04
    Negro
    1.00
     watermelon
    0.97
     lyn
    0.97
    jungle
    0.91
    Activations Density 0.038%

    No Known Activations