© 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. 10-GEMMASCOPE-RES-131K
    7. 118790
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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_10/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
    zość
    -2.67
    เพราะ
    -2.08
     This
    -2.08
    낍
    -2.08
    ers
    -2.08
    。
    -1.96
    ;
    -1.95
    䌀
    -1.94
    лении
    -1.92
     istruzioni
    -1.90
    POSITIVE LOGITS
    </strong>
    2.45
    '
    2.27
     to
    1.84
    section
    1.84
    ?”
    1.80
    
    1.77
     you
    1.77
     the
    1.75
     biały
    1.70
    subsection
    1.70
    Activations Density 0.000%

    No Known Activations