© 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. 34-GEMMASCOPE-RES-131K
    7. 57797
    Prev
    Next
    INDEX
    Explanations

    language and culture

    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
     languages
    -2.02
    语言
    -1.98
     language
    -1.92
    Languages
    -1.91
     Languages
    -1.88
    LANGUAGE
    -1.80
    languages
    -1.77
     LANGUAGE
    -1.73
    語言
    -1.70
    Language
    -1.66
    POSITIVE LOGITS
     culture
    1.09
     cultural
    0.90
    cultural
    0.81
    kultur
    0.80
     Culture
    0.79
    culture
    0.79
     dialects
    0.75
    文化
    0.75
     counties
    0.74
     Computer
    0.72
    Activations Density 0.043%

    No Known Activations