© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 45746
    Prev
    Next
    INDEX
    Explanations

    UAE associated information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    Sebagai
    0.70
     ח
    0.70
     הנ
    0.68
     שי
    0.68
     לה
    0.66
     ס
    0.66
     הפ
    0.64
     למ
    0.64
    Sistema
    0.63
    महल
    0.63
    POSITIVE LOGITS
    ó
    0.78
    for
    0.66
    y
    0.63
    IN
    0.62
    一份
    0.62
    一種
    0.62
     posteriores
    0.61
    我們要
    0.61
    ied
    0.61
    ور
    0.60
    Activations Density 0.003%

    No Known Activations