© 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. 103960
    Prev
    Next
    INDEX
    Explanations

    names of politicians or public figures

    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
    各種
    -1.73
     damski
    -1.67
     deceiving
    -1.59
    .
    -1.59
     continú
    -1.56
     Miß
    -1.56
     Quels
    -1.55
     '"
    -1.55
    CARACTERIST
    -1.55
     étaient
    -1.54
    POSITIVE LOGITS
     who
    2.58
     to
    2.03
    </h1>
    1.98
     not
    1.97
     并
    1.83
    スの
    1.73
     {
    
    1.70
     fisuras
    1.69
     whom
    1.66
     that
    1.64
    Activations Density 0.006%

    No Known Activations