© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40634
    Prev
    Next
    INDEX
    Explanations

    Ohio State and Big Ten Conference

    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
    ,
    -2.42
     适合
    -1.91
     苹果
    -1.89
    原标题
    -1.88
    也算是
    -1.84
     "
    -1.80
     This
    -1.79
    蠵
    -1.78
     Swimming
    -1.78
     ponen
    -1.68
    POSITIVE LOGITS
     spazi
    2.17
     Trabalho
    2.00
    謖
    1.97
    icioso
    1.96
     tessuto
    1.93
     jednego
    1.92
    ܜ
    1.88
     fará
    1.84
    蟶
    1.81
     triumphs
    1.78
    Activations Density 0.004%

    No Known Activations