© 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. 119743
    Prev
    Next
    INDEX
    Explanations

    non-woven materials

    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
     للغ
    -1.76
    鏵
    -1.63
     heading
    -1.61
    衚
    -1.54
    Bagaimana
    -1.53
    </code>
    -1.52
     trovano
    -1.52
    したのが
    -1.52
    Ꮉ
    -1.48
    0
    -1.46
    POSITIVE LOGITS
     و
    2.09
     ו
    1.61
    </h2>
    1.56
     家居
    1.55
     และ
    1.53
     contours
    1.52
    骉
    1.52
     بال
    1.52
    ㎡
    1.52
    梛
    1.48
    Activations Density 0.023%

    No Known Activations