© 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-65K
    7. 3756
    Prev
    Next
    INDEX
    Explanations

    ## topic title

    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
    Negative Logits
     invoc
    1.02
     dismay
    1.01
     développ
    1.00
    他
    0.96
    t
    0.96
     desenvolv
    0.95
     aldı
    0.93
    IS
    0.91
    ാപ
    0.91
     alimentare
    0.91
    POSITIVE LOGITS
    .
    1.46
    س
    1.41
     was
    1.27
    ص
    1.27
    v
    1.24
    ف
    1.21
    '
    1.17
    ج
    1.14
    ح
    1.12
    ons
    1.01
    Activations Density 0.044%

    No Known Activations