© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58273
    Prev
    Next
    INDEX
    Explanations

    tokens following comma or quote

    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
    Not in Any Lists

    No Comments

    Negative Logits
     other
    -1.34
     of
    -1.30
    most
    -1.20
    缺點
    -1.20
     but
    -1.18
     to
    -1.16
    ally
    -1.14
     until
    -1.13
    与此
    -1.09
    詳しくは
    -1.09
    POSITIVE LOGITS
     the
    1.65
    Shaders
    1.45
     your
    1.45
    приєм
    1.33
     his
    1.31
     debacle
    1.30
     fameux
    1.29
    izacja
    1.28
     traditionnels
    1.25
    介绍
    1.21
    Activations Density 0.086%

    No Known Activations