© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68845
    Prev
    Next
    INDEX
    Explanations

    questions and statements

    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
     diriger
    -1.73
     :"
    -1.73
     anunció
    -1.66
     praktisch
    -1.61
     -"
    -1.53
     sentier
    -1.51
     ainfi
    -1.48
     sowieso
    -1.48
     gewi
    -1.47
     استناد
    -1.47
    POSITIVE LOGITS
     which
    2.05
     if
    1.72
     although
    1.70
     because
    1.63
     first
    1.52
    
    1.50
    इटम
    1.49
     while
    1.48
    ၄
    1.48
     when
    1.46
    Activations Density 0.143%

    No Known Activations