© 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. 90959
    Prev
    Next
    INDEX
    Explanations

    language markers in multilingual contexts

    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
     himself
    -2.16
     který
    -1.40
     הראשון
    -1.37
     său
    -1.34
     ktorý
    -1.33
     koji
    -1.32
     الداخلية
    -1.30
     aislada
    -1.30
     został
    -1.26
     نفسه
    -1.23
    POSITIVE LOGITS
     herself
    2.91
     которую
    2.11
     которая
    1.98
     која
    1.81
    herself
    1.71
     laquelle
    1.47
     która
    1.39
     którą
    1.38
     která
    1.33
     koja
    1.31
    Activations Density 0.097%

    No Known Activations