© 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. 65821
    Prev
    Next
    INDEX
    Explanations

    international days and family holidays

    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
    依然
    -0.77
     dah
    -0.75
    тивное
    -0.75
     expuls
    -0.73
    株式会社
    -0.73
     брюки
    -0.72
     dignidad
    -0.71
     ビッグ
    -0.71
     AspNetCore
    -0.71
    鮰
    -0.71
    POSITIVE LOGITS
     Women
    2.19
     Mother
    1.69
     women
    1.55
    Women
    1.55
     Mothers
    1.47
     mother
    1.37
     Womens
    1.32
     mothers
    1.27
     Woman
    1.24
     Father
    1.23
    Activations Density 0.029%

    No Known Activations