© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 90518
    Prev
    Next
    INDEX
    Explanations

    Facades and fines

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     τον
    0.68
    on
    0.67
    ną
    0.66
    一线
    0.64
    верну
    0.63
    and
    0.62
    ılan
    0.62
    сер
    0.62
    ＊
    0.62
     dàng
    0.61
    POSITIVE LOGITS
    ’
    0.64
    ینگ
    0.57
     Scheduled
    0.56
     borr
    0.56
    ウッド
    0.55
     Efficient
    0.55
     Withdrawal
    0.54
     (
    0.54
    뀝
    0.53
     desen
    0.52
    Activations Density 0.001%

    No Known Activations