© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232502
    Prev
    Next
    INDEX
    Explanations

    capacity, examination, cancer, statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     flav
    0.53
     jist
    0.51
     Á
    0.49
    '
    0.49
     aline
    0.49
     lime
    0.48
     wollen
    0.47
     dah
    0.47
     fah
    0.47
     blasp
    0.46
    POSITIVE LOGITS
    你是
    0.56
     bạn
    0.52
    该
    0.52
    懒
    0.52
    判定
    0.51
    Statement
    0.51
    型号
    0.50
    放弃
    0.50
     وإن
    0.50
    电器
    0.49
    Activations Density 0.000%

    No Known Activations