© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39711
    Prev
    Next
    INDEX
    Explanations

    legs

    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
    {
    -2.91
    摃
    -2.63
    聼
    -2.50
    “
    -2.30
     you
    -2.30
    桖
    -2.28
    是怎么回事
    -2.27
    Ꮉ
    -2.22
     will
    -2.22
    扺
    -2.19
    POSITIVE LOGITS
    縢
    2.69
    蹰
    2.63
     wth
    2.61
    
    2.53
    ﮟ
    2.52
     Есть
    2.47
    ዡ
    2.45
     freakin
    2.44
     bilde
    2.34
     других
    2.28
    Activations Density 0.006%

    No Known Activations