© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201153
    Prev
    Next
    INDEX
    Explanations

    racial discrimination

    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_262k_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
     педаго
    0.65
    缡
    0.61
    峤
    0.59
     любы
    0.58
     перспек
    0.57
    гар
    0.56
    黉
    0.56
     народ
    0.55
     аку
    0.55
     любой
    0.54
    POSITIVE LOGITS
    ：
    0.73
     netizens
    0.72
     hahaha
    0.67
    ："
    0.65
     Compared
    0.62
    ಬಹುದು
    0.61
     Uyg
    0.61
     丨
    0.60
     Xia
    0.59
    這個
    0.59
    Activations Density 0.010%

    No Known Activations