© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6042
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     протяжении
    0.80
     setiap
    0.73
    ！！！！
    0.66
    ‼
    0.65
     every
    0.65
     κάθε
    0.64
     Every
    0.63
     countless
    0.62
     EVERY
    0.61
     प्रतिदिन
    0.61
    POSITIVE LOGITS
    /
    0.88
     bzw
    0.63
    ə
    0.62
    우스
    0.61
     उधर
    0.59
     antitrust
    0.59
     원래
    0.58
     egent
    0.57
    /+
    0.57
     etre
    0.57
    Activations Density 0.142%

    No Known Activations