© 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. 127354
    Prev
    Next
    INDEX
    Explanations

    mexico and mexican

    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
    〜〜
    -1.75
     satisfies
    -1.63
     differentiates
    -1.61
     minimizes
    -1.57
     seems
    -1.52
     utilizes
    -1.52
     understands
    -1.51
     =
    -1.51
     recognizes
    -1.48
     realizes
    -1.48
    POSITIVE LOGITS
    CUL
    1.38
     {};
    1.36
    ➕
    1.28
    天津
    1.25
    thodon
    1.25
    FAN
    1.24
    توضیحات
    1.23
    teig
    1.23
     ブルゾン
    1.23
    ASIN
    1.23
    Activations Density 0.090%

    No Known Activations