© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 7590
    Prev
    Next
    INDEX
    Explanations

    Nigerian

    np_max-act-logits · gemini-2.5-flash-lite

    Nigerian cultures

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_16k_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
     በሚ
    0.61
    ähl
    0.59
    हित्य
    0.50
    >\<
    0.50
    辽
    0.49
    짬
    0.48
    Decorative
    0.48
     مشکل
    0.47
     Guwahati
    0.47
    
    0.46
    POSITIVE LOGITS
     Yoruba
    1.20
     Ade
    1.16
    Ade
    1.16
     Ogun
    1.03
     Yor
    1.02
     Olu
    0.99
     Ekiti
    0.94
    ẹ
    0.93
     Oyo
    0.91
     Ol
    0.90
    Activations Density 0.075%

    No Known Activations