© 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. 71419
    Prev
    Next
    INDEX
    Explanations

    win-win

    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
    אם
    -1.72
     -¿
    -1.69
    Dzień
    -1.67
    Ако
    -1.66
    konfirmasi
    -1.56
    Witaj
    -1.53
    આ
    -1.52
    了一会儿
    -1.51
     violeta
    -1.49
    האם
    -1.48
    POSITIVE LOGITS
     and
    2.08
     your
    1.91
     You
    1.57
    镡
    1.49
     usar
    1.37
     is
    1.35
     и
    1.31
    糌
    1.30
     shown
    1.30
     was
    1.30
    Activations Density 0.003%

    No Known Activations