© 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. 81533
    Prev
    Next
    INDEX
    Explanations

    culture and its descriptions

    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
    ervices
    -0.89
    手中的
    -0.85
    lies
    -0.82
    content
    -0.78
    cheme
    -0.76
    รก
    -0.73
    lizes
    -0.73
    atives
    -0.73
    º
    -0.73
     CONTENT
    -0.72
    POSITIVE LOGITS
     culture
    5.31
     Culture
    3.83
    culture
    3.80
     cultures
    3.70
    Culture
    3.47
    文化
    3.30
     CULTURE
    3.14
     культуры
    3.06
    CULTURE
    2.80
     cultura
    2.77
    Activations Density 0.051%

    No Known Activations