© 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. 34-GEMMASCOPE-RES-131K
    7. 77356
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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_34/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
    而成
    -0.98
     histórico
    -0.93
    aconda
    -0.90
     RÉ
    -0.89
    vieran
    -0.89
     DÉ
    -0.88
     ★★★
    -0.87
     jugu
    -0.87
    Parameteri
    -0.86
     cend
    -0.84
    POSITIVE LOGITS
    UT
    0.97
     patent
    0.94
     Patent
    0.93
     principalement
    0.91
     farklı
    0.91
     vooral
    0.91
    WHY
    0.90
     обязательно
    0.89
     pozwala
    0.89
     polega
    0.89
    Activations Density 0.012%

    No Known Activations