© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10986
    Prev
    Next
    INDEX
    Explanations

    URLs and specific sites

    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
    絲
    0.45
    静
    0.43
    kta
    0.41
     privados
    0.41
    ्युअर
    0.40
    纳米
    0.40
     식품
    0.39
    GN
    0.38
    Dados
    0.38
    丝
    0.38
    POSITIVE LOGITS
     Github
    0.47
    මාණය
    0.44
    hamdulillah
    0.43
    <unused100>
    0.40
    azaar
    0.39
    ripsi
    0.39
     Novem
    0.38
    ergewöhn
    0.38
     চায়
    0.38
    hamdul
    0.38
    Activations Density 0.045%

    No Known Activations