© 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. 10-GEMMASCOPE-RES-131K
    7. 21170
    Prev
    Next
    INDEX
    Explanations

    adverbs of concession

    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
     {
    -2.33
     

    -1.98
     cuddling
    -1.95
     Также
    -1.95
     Затем
    -1.91
     avid
    -1.90
    </u>
    -1.90
     Еще
    -1.86
    ically
    -1.82
     précisé
    -1.78
    POSITIVE LOGITS
     này
    2.08
    鈈
    2.03
    蘼
    2.02
     این
    2.00
    鸶
    1.98
    .");
    1.96
    this
    1.95
    mittedly
    1.93
     Chrif
    1.87
    ,;
    1.86
    Activations Density 0.003%

    No Known Activations