© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72220
    Prev
    Next
    INDEX
    Explanations

    mathematic operators or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    やはり
    -1.77
    </sup>
    -1.62
    ”
    -1.60
     maravillosas
    -1.52
     «
    -1.52
     السياس
    -1.49
    鋱
    -1.47
    ί
    -1.45
    竟然
    -1.44
    让他
    -1.44
    POSITIVE LOGITS
     to
    2.11
     with
    1.85
     for
    1.83
     other
    1.65
     most
    1.55
     including
    1.55
     by
    1.52
     ۱۶
    1.47
     only
    1.47
     on
    1.46
    Activations Density 0.146%

    No Known Activations