Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 102
    Prev
    Next
    INDEX
    Explanations

    to the

    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_16_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
    t
    0.67
    ليو
    0.54
    ريبا
    0.53
    لي
    0.51
    дів
    0.51
     sj
    0.50
    ্যালি
    0.50
     zus
    0.49
     condomin
    0.49
    دق
    0.49
    POSITIVE LOGITS
    께서
    0.60
    ęła
    0.59
    ita
    0.57
    itty
    0.57
    5
    0.56
    ające
    0.55
    ad
    0.55
    commonly
    0.55
     آیا
    0.54
     दिशा
    0.53
    Activations Density 0.001%

    No Known Activations