© 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. 22-GEMMASCOPE-RES-131K
    7. 72920
    Prev
    Next
    INDEX
    Explanations

    High copy number or published

    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_22/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
    қы
    -1.03
     of
    -0.98
     EventArgs
    -0.96
    場合は
    -0.96
    佷
    -0.93
     }{@
    -0.92
    ्यान
    -0.91
    LayoutStyle
    -0.90
     parámetros
    -0.90
     интервью
    -0.88
    POSITIVE LOGITS
     four
    1.09
     two
    1.07
    engertian
    1.04
     따라
    0.99
     only
    0.99
    apartamento
    0.99
     five
    0.98
     ustedes
    0.97
     three
    0.97
     what
    0.94
    Activations Density 0.028%

    No Known Activations