© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73789
    Prev
    Next
    INDEX
    Explanations

    stages of

    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
     is
    -1.81
    出了一
    -1.66
     It
    -1.66
     
    -1.65
     has
    -1.58
    色は
    -1.55
    教科
    -1.54
     something
    -1.53
    IANGLES
    -1.50
    盌
    -1.48
    POSITIVE LOGITS
     defekt
    2.08
     炒め
    1.98
     your
    1.91
    ::<
    1.73
     our
    1.73
     their
    1.71
    ława
    1.64
    蒞
    1.63
    地區
    1.63
    比賽
    1.59
    Activations Density 0.039%

    No Known Activations