© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 7059
    Prev
    Next
    INDEX
    Explanations

    racism, racial discrimination, stereotypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ধর্ম
    0.48
     DHL
    0.45
    实际
    0.39
     Alters
    0.39
    递
    0.38
     propi
    0.38
     GSK
    0.38
    倾
    0.38
    国际
    0.38
     ধর্ম
    0.37
    POSITIVE LOGITS
     racial
    0.58
     interracial
    0.55
     racist
    0.52
     Colored
    0.50
     theaters
    0.50
    colored
    0.49
     blacks
    0.49
     colored
    0.49
     आजही
    0.48
     racism
    0.47
    Activations Density 0.202%

    No Known Activations