© 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. 21489
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    hesia
    0.43
    说完
    0.42
     unchanging
    0.42
     uplift
    0.41
     adhered
    0.40
    件事
    0.39
    上去
    0.39
    跳
    0.38
    sil
    0.38
     jumping
    0.38
    POSITIVE LOGITS
     чтобы
    0.54
     exposing
    0.54
     Dadurch
    0.52
    以便
    0.50
     ताकि
    0.49
     sodass
    0.49
    面对
    0.47
     щоб
    0.46
     zodat
    0.46
     Sehingga
    0.46
    Activations Density 0.001%

    No Known Activations