© 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. 69057
    Prev
    Next
    INDEX
    Explanations

    Wi-Fi

    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
    m
    -2.80
    \
    -2.59
    ,”
    -2.50
    ,’
    -2.42
    2
    -2.39
    ”
    -2.38
    "
    -2.33
    al
    -2.33
    A
    -2.31
    si
    -2.27
    POSITIVE LOGITS
    柃
    2.09
    硨
    2.02
    逐渐
    2.02
     But
    1.81
     complic
    1.73
    
    1.72
    賅
    1.67
    すすめ
    1.66
     dud
    1.65
     -
    1.64
    Activations Density 0.004%

    No Known Activations