© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67964
    Prev
    Next
    INDEX
    Explanations

    SQL query values

    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
    tahan
    -0.98
    lyt
    -0.92
     только
    -0.91
    usul
    -0.90
     even
    -0.89
     Produtos
    -0.89
    ява
    -0.88
     to
    -0.88
     következő
    -0.88
    ⤒
    -0.87
    POSITIVE LOGITS
    Ĺ
    1.00
    相机
    0.97
    他們
    0.91
    ⽉
    0.91
    ものである
    0.90
     жк
    0.90
    ii
    0.90
    िति
    0.89
     oğ
    0.88
     хотят
    0.88
    Activations Density 0.018%

    No Known Activations