© 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. 28588
    Prev
    Next
    INDEX
    Explanations

    better improvement

    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
    il
    0.85
     എടു
    0.70
    ле
    0.68
     jede
    0.67
    indeki
    0.64
    ul
    0.63
    ত
    0.63
    lə
    0.62
     vile
    0.61
    لية
    0.61
    POSITIVE LOGITS
    시
    0.73
    。
    0.66
     is
    0.64
    ف
    0.64
    กระ
    0.64
    ג
    0.64
    Não
    0.62
    पणे
    0.62
    く
    0.62
    지
    0.61
    Activations Density 0.006%

    No Known Activations