© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130463
    Prev
    Next
    INDEX
    Explanations

    code keywords and symbols

    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
    囝
    -0.98
     çünkü
    -0.92
    哏
    -0.91
     alguns
    -0.89
     logiciel
    -0.89
     besonder
    -0.88
    !/
    -0.87
    屁股
    -0.87
    ^,
    -0.86
    йтинг
    -0.86
    POSITIVE LOGITS
     at
    1.38
     will
    1.15
    While
    1.08
    如图
    1.03
     should
    1.02
     can
    1.02
    There
    1.01
    今回は
    1.00
     thôi
    0.98
     only
    0.97
    Activations Density 0.007%

    No Known Activations