© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46426
    Prev
    Next
    INDEX
    Explanations

    contrast or explanation

    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
     Кур
    0.45
     Н
    0.44
     Ре
    0.44
     極
    0.44
     পাশ
    0.43
     авгу
    0.43
    ленный
    0.43
     разработан
    0.43
     স্বেচ্ছ
    0.42
     Eye
    0.41
    POSITIVE LOGITS
     uden
    0.46
     either
    0.44
     farce
    0.43
    /{
    0.41
    라스
    0.41
    cole
    0.41
    而不是
    0.41
    없이
    0.40
    你说
    0.40
    debt
    0.39
    Activations Density 0.015%

    No Known Activations