© 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. 21678
    Prev
    Next
    INDEX
    Explanations

    Chang and associated names or places

    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
    
    -2.98
    簠
    -2.86
    
    -2.61
     serán
    -2.58
     involucrados
    -2.55
     alguns
    -2.52
     ใน
    -2.44
     alcuni
    -2.44
    kové
    -2.42
     使っ
    -2.42
    POSITIVE LOGITS
     was
    3.44
    乆
    2.77
    m
    2.69
     exquisite
    2.67
     This
    2.61
    {
    2.59
    蕯
    2.58
    g
    2.56
    舠
    2.55
    结语
    2.48
    Activations Density 0.002%

    No Known Activations