© 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. 10-GEMMASCOPE-RES-131K
    7. 61234
    Prev
    Next
    INDEX
    Explanations

    quantities and units

    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
      
    -2.11
     thuy
    -1.64
     vong
    -1.55
     heo
    -1.54
     xay
    -1.48
    at
    -1.47
     dì
    -1.45
     nuoc
    -1.45
     nhat
    -1.43
     quà
    -1.42
    POSITIVE LOGITS
     banyo
    1.70
     ordini
    1.69
     kimdir
    1.68
     chiare
    1.63
     esso
    1.62
     nasıl
    1.61
     bardak
    1.59
    ！"
    1.59
    quelize
    1.59
    ！！！
    1.59
    Activations Density 0.041%

    No Known Activations