© 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. 48502
    Prev
    Next
    INDEX
    Explanations

    fluffy, whipped, candy, mounding, puffy, sparkling

    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
    ↵
    -1.84
     ,‬
    -1.63
    re
    -1.55
    R
    -1.54
    </i>
    -1.54
    IC
    -1.52
    ID
    -1.52
    k
    -1.48
    鲼
    -1.45
     eixo
    -1.42
    POSITIVE LOGITS
    垕
    1.63
    皤
    1.59
     systé
    1.59
     lidé
    1.57
    iç
    1.55
     คุณ
    1.52
     детьми
    1.51
    untuk
    1.48
     Вам
    1.48
    Список
    1.47
    Activations Density 0.016%

    No Known Activations