© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3727
    Prev
    Next
    INDEX
    Explanations

    South Africa and Mandela

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     pprint
    0.81
     parentheses
    0.74
     調
    0.73
     vapors
    0.72
    滤波器
    0.70
     Є
    0.69
     প্রয়োগ
    0.69
    舝
    0.69
     உண்ட
    0.68
    拽
    0.68
    POSITIVE LOGITS
     Johannesburg
    2.46
     Gauteng
    2.25
     KwaZulu
    2.24
     Pretoria
    2.21
     Cape
    2.21
     Durban
    2.17
     Afrika
    2.17
    Cape
    2.12
     South
    2.09
    🇿
    2.08
    Activations Density 0.050%

    No Known Activations