© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3659
    Prev
    Next
    INDEX
    Explanations

    compiling, comprehensive, compute, command

    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_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
    س
    1.22
    ا
    1.05
    )，
    1.00
    מ
    0.98
    ف
    0.98
    ли
    0.98
    ن
    0.94
    го
    0.93
    اج
    0.90
    г
    0.90
    POSITIVE LOGITS
    at
    1.20
    ۹
    1.15
    ine
    1.05
    ar
    1.01
    る
    0.99
    >
    0.98
    {
    0.97
    an
    0.96
    r
    0.96
    inin
    0.96
    Activations Density 0.317%

    No Known Activations