© 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. 19738
    Prev
    Next
    INDEX
    Explanations

    css, javascript, platform, tpu

    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
    in
    1.04
    a
    0.97
    u
    0.90
    t
    0.86
    ized
    0.84
    form
    0.77
    ight
    0.76
    er
    0.74
    o
    0.73
     Spartans
    0.72
    POSITIVE LOGITS
    ع
    0.83
     anderes
    0.79
    ط
    0.77
    ق
    0.74
    ش
    0.72
    ש
    0.72
    لا
    0.71
    را
    0.70
    أ
    0.70
     продукты
    0.69
    Activations Density 0.000%

    No Known Activations