© 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. 41-GEMMASCOPE-2-RES-262K
    7. 30052
    Prev
    Next
    INDEX
    Explanations

    interface, harina, flour, huevos, grandes, açúcar

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     स्वचालित
    0.46
    黾
    0.44
     सकेगा
    0.43
    臬
    0.43
    倬
    0.42
    গাল
    0.42
    蹇
    0.42
    欵
    0.42
     adhesives
    0.41
    选手
    0.41
    POSITIVE LOGITS
     marinade
    0.48
     pickles
    0.47
     "
    0.46
     harina
    0.46
     flour
    0.44
     Vegeta
    0.43
     inter
    0.42
     açúcar
    0.42
     Soda
    0.42
     abund
    0.42
    Activations Density 0.008%

    No Known Activations