© 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. 12577
    Prev
    Next
    INDEX
    Explanations

    signed followed by what

    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
    {
    -3.31
    n
    -3.11
    “
    -2.92
     "
    -2.63
     decide
    -2.52
     बहुत
    -2.52
     .
    -2.48
    ’
    -2.47
     I
    -2.42
     “
    -2.39
    POSITIVE LOGITS
    雰囲
    2.95
    欵
    2.94
    　　「
    2.94
     現貨
    2.81
     遊戲
    2.75
     迷你
    2.75
    
    2.73
    Зно
    2.67
    
    2.66
    In
    2.59
    Activations Density 0.008%

    No Known Activations