© 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. 9752
    Prev
    Next
    INDEX
    Explanations

    ann followed by names or parts of other words

    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
     are
    -2.91
     It
    -2.83
     ähnlichen
    -2.75
     höheren
    -2.64
     In
    -2.61
     speziellen
    -2.56
     gemeinsamen
    -2.47
     zahlreichen
    -2.47
     kurzen
    -2.41
    匆
    -2.38
    POSITIVE LOGITS
    Ꮉ
    3.59
    勠
    3.03
    n
    2.95
    k
    2.95
    IN
    2.94
    h
    2.83
    '
    2.66
    焢
    2.56
    
    2.50
     學
    2.48
    Activations Density 0.007%

    No Known Activations