© 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. 38764
    Prev
    Next
    INDEX
    Explanations

    pro-

    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
     
    -1.96
    /");
    -1.84
    ↵↵
    -1.81
     aña
    -1.80
     are
    -1.80
     jeżeli
    -1.80
     crucial
    -1.78
    皛
    -1.73
     `
    -1.73
    )=\
    -1.71
    POSITIVE LOGITS
    Жит
    2.36
    Ведущий
    2.09
    Кому
    2.09
    佧
    2.06
    Цитата
    2.06
    Веду
    2.03
    Despite
    2.03
     hamil
    1.98
    Подготовка
    1.97
    綑
    1.95
    Activations Density 0.004%

    No Known Activations