© 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. 14925
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     what
    -1.86
     how
    -1.59
    :}
    -1.55
     then
    -1.54
    :
    -1.50
     sekitarnya
    -1.49
    喏
    -1.40
    ènements
    -1.37
     kuv
    -1.34
     subsequently
    -1.30
    POSITIVE LOGITS
     disait
    1.46
     voulait
    1.39
    閙
    1.35
     době
    1.33
     эту
    1.32
    return
    1.27
     trouvait
    1.27
     espagnol
    1.26
    asuring
    1.26
    ですが
    1.26
    Activations Density 0.115%

    No Known Activations