© 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. 22-GEMMASCOPE-RES-131K
    7. 36413
    Prev
    Next
    INDEX
    Explanations

    is called or namely

    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_22/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
     vías
    -0.89
     śpiew
    -0.87
     sendo
    -0.84
     auténtica
    -0.84
    邉
    -0.80
     whereas
    -0.78
     mendorong
    -0.77
    bài
    -0.77
    uncia
    -0.77
     accessing
    -0.77
    POSITIVE LOGITS
    这就是
    0.93
     namely
    0.88
     Namely
    0.84
    namely
    0.79
    名称
    0.79
     kesi
    0.79
     речь
    0.78
     män
    0.77
     называется
    0.77
     of
    0.76
    Activations Density 0.070%

    No Known Activations