© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44624
    Prev
    Next
    INDEX
    Explanations

    Uganda and Ugandan

    np_acts-logits-general · gemini-2.5-flash-lite

    Uganda, genocide, railway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Durban
    0.43
     пере
    0.40
    胍
    0.40
     oyn
    0.39
     ваго
    0.38
    ‴
    0.38
     Paloma
    0.38
     収納
    0.38
     लेन
    0.38
    樽
    0.37
    POSITIVE LOGITS
     Uganda
    0.71
     Kampala
    0.70
     Ugandan
    0.69
    Ug
    0.61
     Rw
    0.47
     ug
    0.47
     Ug
    0.45
    कांड
    0.43
     तहरीर
    0.43
     कांड
    0.39
    Activations Density 0.013%

    No Known Activations