© 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. 34-GEMMASCOPE-RES-131K
    7. 82269
    Prev
    Next
    INDEX
    Explanations

    quantities and approximations

    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
     people
    -0.90
    kawa
    -0.86
    राम
    -0.85
    燜
    -0.82
     dizaine
    -0.81
    masses
    -0.79
    drei
    -0.79
    Читати
    -0.79
     Celebrities
    -0.78
    ELES
    -0.78
    POSITIVE LOGITS
     thousands
    1.41
    thousands
    1.25
     тысячи
    1.20
    Thousands
    1.13
     Thousands
    1.09
     yaklaşık
    0.98
     Approximately
    0.96
     примерно
    0.96
     milliers
    0.93
     khoảng
    0.87
    Activations Density 0.047%

    No Known Activations