© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    тинг
    0.73
    ров
    0.71
    ")
    0.71
    e
    0.70
     gimmick
    0.70
    в
    0.68
     dieting
    0.66
    EN
    0.63
    jquery
    0.63
    анг
    0.62
    POSITIVE LOGITS
    त्ती
    0.96
    ية
    0.87
     الأساس
    0.81
    लिट
    0.78
    І
    0.77
    اي
    0.77
     عطا
    0.75
    احة
    0.75
     intensidade
    0.75
     resposta
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.