© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27901
    Prev
    Next
    INDEX
    Explanations

    while loops

    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_22/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
     火鍋
    -1.08
    توضیحات
    -1.02
    Ḏ
    -1.02
    UEGO
    -1.00
    談社
    -0.99
    Charakter
    -0.98
    CreatedBy
    -0.95
     grijs
    -0.95
     手绘
    -0.94
    Karakter
    -0.94
    POSITIVE LOGITS
     проверить
    0.89
    mfrac
    0.89
    зий
    0.88
     formulario
    0.85
     selfless
    0.84
     neuen
    0.81
     zuverläs
    0.80
     示例
    0.80
     آیا
    0.80
    try
    0.80
    Activations Density 0.003%

    No Known Activations