© 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. 31-GEMMASCOPE-2-RES-262K
    7. 2394
    Prev
    Next
    INDEX
    Explanations

    parentheses and slashes

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ുവരി
    0.28
    VARCHAR
    0.26
    }^{+}=
    0.25
    ыз
    0.24
     sphinct
    0.24
     épars
    0.24
    ूरती
    0.24
    ীয়তে
    0.23
    Lucene
    0.23
     preconceived
    0.23
    POSITIVE LOGITS
     ,
    0.24
     、
    0.23
     Đ
    0.23
     or
    0.23
     och
    0.22
    をはじめ
    0.22
     Lech
    0.22
    ı
    0.22
     उ
    0.21
     وغ
    0.21
    Activations Density 0.745%

    No Known Activations