© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7248
    Prev
    Next
    INDEX
    Explanations

    time stamps and court documents

    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
    ׇ
    -2.03
     блюдо
    -1.98
     chré
    -1.98
     الجلد
    -1.89
    ֩
    -1.86
     catholique
    -1.78
     τὰ
    -1.73
     ܐ
    -1.73
    ֺ
    -1.70
     chrétienne
    -1.70
    POSITIVE LOGITS
    ּוֹ
    2.50
     السياس
    2.39
    ִּ
    1.90
    民众
    1.87
    ַּ
    1.75
    选举
    1.73
    官员
    1.62
    וּ
    1.62
     бампер
    1.62
    ְּ
    1.61
    Activations Density 0.263%

    No Known Activations