© 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. 59512
    Prev
    Next
    INDEX
    Explanations

    african american and black

    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
     xen
    -0.96
     settler
    -0.93
     whitish
    -0.82
    FEMALE
    -0.81
     Immigrant
    -0.78
     mutil
    -0.77
    LGBT
    -0.76
     LGBTQ
    -0.76
    WOMEN
    -0.75
    र्ष
    -0.75
    POSITIVE LOGITS
     black
    2.75
     African
    2.28
     Black
    2.14
    black
    2.02
     BLACK
    1.88
    BLACK
    1.88
    Black
    1.80
     blacks
    1.80
    黒
    1.72
    African
    1.70
    Activations Density 0.049%

    No Known Activations