© 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. 67312
    Prev
    Next
    INDEX
    Explanations

    better way

    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
     概念
    -2.19
    鹮
    -2.11
     to
    -1.77
     经典
    -1.72
    ༀ
    -1.66
    Transporte
    -1.64
    凩
    -1.62
     綺麗
    -1.61
     供
    -1.59
     anunció
    -1.59
    POSITIVE LOGITS
     cueva
    2.09
     carcasa
    1.94
     thing
    1.90
     estekak
    1.88
    或
    1.87
    
    1.74
     cuna
    1.73
     gorra
    1.73
     alfombra
    1.71
    𝐁
    1.70
    Activations Density 0.030%

    No Known Activations