© 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. 10-GEMMASCOPE-RES-131K
    7. 11344
    Prev
    Next
    INDEX
    Explanations

    patency, patently, patellar, patents

    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
    </h3>
    -3.17
    荅
    -2.75
    。"
    -2.63
    𐄁
    -2.61
    嗽
    -2.56
    人也
    -2.55
    鈊
    -2.41
    錞
    -2.30
     \_
    -2.30
    诹
    -2.28
    POSITIVE LOGITS
    </b>
    3.66
    {
    3.36
    そういえば
    3.06
    1
    2.88
    6
    2.86
    [
    2.73
    ,”
    2.72
    经常
    2.70
    '
    2.55
    無法
    2.53
    Activations Density 0.029%

    No Known Activations