© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2432
    Prev
    Next
    INDEX
    Explanations

    KwaZulu-Natal geographies

    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_all/layer_41_width_262k_l0_big
    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
    '][:
    0.44
     calibrations
    0.40
    }\{
    0.40
    responseData
    0.39
    ݢ
    0.39
    คะ
    0.38
     (\<
    0.38
    𒃲
    0.38
    在北京
    0.38
     ஏற்றுக்கொள்ள
    0.38
    POSITIVE LOGITS
     Durban
    1.17
     KwaZulu
    1.17
    Zulu
    0.89
     Zulu
    0.85
     부산
    0.77
    Natal
    0.73
    Kwa
    0.72
    부산
    0.69
     Natal
    0.68
    QString
    0.64
    Activations Density 0.001%

    No Known Activations