© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10563
    Prev
    Next
    INDEX
    Explanations

    это followed by a noun

    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
     químicas
    -1.77
     "...
    -1.77
    на
    -1.75
     PLEASE
    -1.74
    ="
    -1.66
    %;
    -1.63
    捩
    -1.59
     específicas
    -1.58
    queryInterface
    -1.58
     "
    -1.57
    POSITIVE LOGITS
    了你
    1.77
    ྵ
    1.66
     auffi
    1.66
    were
    1.63
    かは
    1.56
     rubio
    1.55
    ჻
    1.54
    点点头
    1.52
    鼕
    1.52
     anny
    1.51
    Activations Density 0.003%

    No Known Activations