© 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. 34-GEMMASCOPE-RES-131K
    7. 81562
    Prev
    Next
    INDEX
    Explanations

    Copyright or license

    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
     слов
    -0.82
     мину
    -0.80
     selama
    -0.78
     podem
    -0.78
     algumas
    -0.77
     duradero
    -0.75
    Notae
    -0.73
    كتور
    -0.73
    tweet
    -0.71
     hypocrite
    -0.71
    POSITIVE LOGITS
    resten
    0.87
     winding
    0.86
     Fernseh
    0.84
    Ǩ
    0.84
     kitchens
    0.81
     Discount
    0.80
     передач
    0.80
     nekem
    0.79
    ۣ
    0.79
    рующие
    0.77
    Activations Density 0.002%

    No Known Activations