© 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. 56026
    Prev
    Next
    INDEX
    Explanations

    German and French words, proper nouns

    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
     under
    -1.07
     під
    -0.88
     под
    -0.80
    Under
    -0.76
    راج
    -0.72
    Lean
    -0.71
     dưới
    -0.70
     debajo
    -0.68
     дел
    -0.66
    under
    -0.66
    POSITIVE LOGITS
    PRODUC
    0.74
     Fontaine
    0.73
    鳟
    0.69
     hundert
    0.69
     Voit
    0.68
    CONVERT
    0.68
     nici
    0.68
    dateien
    0.68
     protéger
    0.67
    garanti
    0.67
    Activations Density 0.069%

    No Known Activations