© 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. 22160
    Prev
    Next
    INDEX
    Explanations

    speakers of various european languages

    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
     chré
    -1.94
     设计
    -1.92
    きれいな
    -1.80
     入力
    -1.79
     catholique
    -1.79
    TASKS
    -1.77
     οὐ
    -1.73
    再一次
    -1.70
     ܐ
    -1.69
     安装
    -1.68
    POSITIVE LOGITS
     or
    2.56
    וּ
    2.31
     your
    2.22
     бампер
    2.11
    ּוֹ
    2.08
     السياس
    2.00
    ַּ
    1.89
    ִּ
    1.88
    ֶּ
    1.88
    选举
    1.82
    Activations Density 0.013%

    No Known Activations