© 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. 58999
    Prev
    Next
    INDEX
    Explanations

    foreign languages and their abbreviations

    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
    <0xA3>
    -0.96
    GIE
    -0.85
    があり
    -0.85
     länder
    -0.83
    鉤
    -0.82
    についての
    -0.81
     SPECIES
    -0.79
    もしか
    -0.78
     ihan
    -0.78
     häm
    -0.78
    POSITIVE LOGITS
     вовсе
    1.38
    ところに
    0.93
    的确
    0.91
    Fortunately
    0.88
    But
    0.87
     कृपया
    0.86
    However
    0.83
    場所で
    0.82
     famously
    0.81
    やう
    0.80
    Activations Density 0.018%

    No Known Activations