© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84593
    Prev
    Next
    INDEX
    Explanations

    html document preamble

    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
    も行
    -1.70
     jednego
    -1.67
     моей
    -1.66
     слыша
    -1.56
    囖
    -1.55
    則是
    -1.54
     защото
    -1.51
     온
    -1.49
     моего
    -1.48
    鹀
    -1.48
    POSITIVE LOGITS
    !”
    1.87
    !”
    1.81
    ?”
    1.62
     with
    1.62
    to
    1.61
    数
    1.60
    ”).
    1.56
     formidable
    1.55
     makeshift
    1.55
     for
    1.52
    Activations Density 0.023%

    No Known Activations