© 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. 3737
    Prev
    Next
    INDEX
    Explanations

    academic study contexts

    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
    ला
    1.59
    2
    1.28
    مان
    1.26
    на
    1.16
    ne
    1.09
    ่
    0.99
    ת
    0.97
    ani
    0.95
    mp
    0.93
    ू
    0.92
    POSITIVE LOGITS
    _
    1.47
     ==============
    1.24
     ﺍ
    1.23
    in
    1.21
     Цена
    1.20
     изу
    1.18
     وقتی
    1.17
     Ако
    1.17
    i
    1.17
    ス
    1.17
    Activations Density 0.022%

    No Known Activations