© 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. 10159
    Prev
    Next
    INDEX
    Explanations

    sequences starting with 1

    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
     now
    -2.50
     the
    -2.27
     by
    -1.98
     ajudam
    -1.98
     not
    -1.91
     può
    -1.90
     そう
    -1.78
     nuovo
    -1.75
     caminha
    -1.69
    -
    -1.66
    POSITIVE LOGITS
    或者
    2.22
     เป็น
    2.17
    
    2.09
    kleidung
    1.96
     språk
    1.95
    灃
    1.94
     bidra
    1.93
    jų
    1.92
    我的
    1.91
    CurtirCurtir
    1.90
    Activations Density 0.013%

    No Known Activations