© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 119911
    Prev
    Next
    INDEX
    Explanations

    Ku Klux Klan, Jim Crow era, laws

    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
     can
    0.66
    の通販
    0.58
     UAV
    0.57
     jotka
    0.57
    ﺕ
    0.56
     capables
    0.56
    LOLL
    0.56
    كين
    0.55
    )^
    0.54
    ছিলাম
    0.54
    POSITIVE LOGITS
    <0x0D>
    0.77
    strates
    0.70
    é
    0.62
    encia
    0.62
    ong
    0.61
    enza
    0.61
    他在
    0.61
     него
    0.60
    him
    0.59
    pero
    0.58
    Activations Density 0.000%

    No Known Activations