© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116548
    Prev
    Next
    INDEX
    Explanations

    married couple's children

    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_34/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
     then
    -0.97
     especially
    -0.95
     freshly
    -0.92
    大量的
    -0.92
     new
    -0.90
     for
    -0.89
     while
    -0.87
     begins
    -0.84
     bietet
    -0.83
     specifically
    -0.82
    POSITIVE LOGITS
    有一個
    1.25
    Together
    1.12
    有两个
    1.12
     kaksi
    1.12
     two
    1.07
     children
    1.05
    three
    1.05
    Children
    1.03
     équipements
    1.02
     twin
    1.01
    Activations Density 0.027%

    No Known Activations