© 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. 59353
    Prev
    Next
    INDEX
    Explanations

    url and url=

    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
     which
    -1.95
     to
    -1.89
     for
    -1.85
     those
    -1.85
     an
    -1.65
     a
    -1.65
     some
    -1.63
     if
    -1.52
     trabaj
    -1.48
     ensuring
    -1.48
    POSITIVE LOGITS
    澌
    1.61
    LLLL
    1.57
    without
    1.55
    ية
    1.50
    
    1.48
     Dinas
    1.48
    щита
    1.48
    This
    1.48
    茹で
    1.47
     рішення
    1.47
    Activations Density 0.000%

    No Known Activations