© 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-65K
    7. 53949
    Prev
    Next
    INDEX
    Explanations

    equal to, multiple tables, incredibly dangerous

    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_65k_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
    真
    0.46
    kat
    0.44
    ند
    0.43
    一方
    0.41
    八
    0.41
    衛星
    0.40
    近年
    0.40
     ri
    0.40
     eight
    0.40
     काप
    0.39
    POSITIVE LOGITS
     представи
    0.53
    ियों
    0.53
    ূর্ত
    0.52
    ение
    0.51
     FormData
    0.48
    اتج
    0.47
     fieldwork
    0.47
     sổ
    0.47
    Czas
    0.47
    icija
    0.46
    Activations Density 0.017%

    No Known Activations