© 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. 40-GEMMASCOPE-2-RES-262K
    7. 24833
    Prev
    Next
    INDEX
    Explanations

    new condition

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     바꿔
    0.39
    éricos
    0.38
    苌
    0.38
     bagay
    0.38
    obaan
    0.37
     değiş
    0.36
     சிக்க
    0.36
    ulfide
    0.35
    ඨ
    0.35
     popularized
    0.35
    POSITIVE LOGITS
     new
    2.36
    new
    2.17
     নতুন
    1.95
     جديد
    1.87
     новых
    1.86
     yeni
    1.84
     nieuwe
    1.84
     nueva
    1.82
     новые
    1.81
    新規
    1.80
    Activations Density 0.010%

    No Known Activations