© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3329
    Prev
    Next
    INDEX
    Explanations

    non-english text

    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_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
    <0x0D>
    0.64
    il
    0.59
    iv
    0.56
    an
    0.56
    r
    0.56
    ut
    0.55
    었다
    0.55
    os
    0.55
    ל
    0.54
    a
    0.54
    POSITIVE LOGITS
     člove
    0.55
     więks
    0.53
     pengetahuan
    0.52
     বাসস্থান
    0.52
     imasmim
    0.52
     façon
    0.52
     nosso
    0.52
     মানুষের
    0.51
     pekerjaan
    0.51
     thành
    0.51
    Activations Density 0.513%

    No Known Activations