© 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. 3417
    Prev
    Next
    INDEX
    Explanations

    multi-language tokens

    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
     своими
    0.52
     страница
    0.49
    なった
    0.48
    際は
    0.48
    тория
    0.47
     シート
    0.46
    釗
    0.44
    âche
    0.44
     Екатерина
    0.44
     recognised
    0.44
    POSITIVE LOGITS
    Assert
    0.59
    cu
    0.51
    ('
    0.48
    을
    0.47
    #'
    0.46
    Id
    0.46
    정
    0.45
     verpflicht
    0.45
    pat
    0.44
     expand
    0.44
    Activations Density 0.000%

    No Known Activations