© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4215
    Prev
    Next
    INDEX
    Explanations

    harmful 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_16_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
    kę
    1.17
     phận
    1.17
    த்தை
    1.16
    り
    1.16
    ž
    1.16
    larım
    1.15
     thermoplastics
    1.15
    leri
    1.14
    ları
    1.13
    larını
    1.13
    POSITIVE LOGITS
    '
    1.50
    น
    1.45
    ა
    1.44
    >
    1.37
    ه
    1.34
    ו
    1.32
    น้อง
    1.31
    a
    1.25
    $
    1.23
    تون
    1.21
    Activations Density 0.173%

    No Known Activations