© 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. 7177
    Prev
    Next
    INDEX
    Explanations

    round robin

    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
    Для
    -0.79
    佣
    -0.79
     нам
    -0.78
     alltså
    -0.77
     назвать
    -0.76
     return
    -0.75
    JR
    -0.75
    iete
    -0.73
    Backward
    -0.73
    Бу
    -0.73
    POSITIVE LOGITS
     robin
    1.74
     ROUND
    1.47
    trip
    1.44
    robin
    1.40
    about
    1.34
    round
    1.32
     round
    1.27
     Round
    1.26
    Round
    1.24
    trips
    1.23
    Activations Density 0.019%

    No Known Activations