© 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. 34-GEMMASCOPE-RES-131K
    7. 94131
    Prev
    Next
    INDEX
    Explanations

    words starting with Ju or Jul

    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_34/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
    儸
    -0.73
    正常的
    -0.71
    meren
    -0.71
    aths
    -0.70
     daraus
    -0.68
    VERT
    -0.68
     Squadron
    -0.66
    atum
    -0.66
     минимум
    -0.65
    ोग
    -0.64
    POSITIVE LOGITS
    ATON
    0.81
    jub
    0.79
    jąc
    0.79
    dice
    0.78
    uju
    0.77
    ɦ
    0.77
     geschenk
    0.77
    も良い
    0.77
    €.
    0.73
    ITÀ
    0.72
    Activations Density 0.023%

    No Known Activations