© 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. 73057
    Prev
    Next
    INDEX
    Explanations

    time ago

    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
     tijdens
    -1.52
     Aunque
    -1.52
    䊐
    -1.52
     alanı
    -1.51
     insatiable
    -1.47
     bebés
    -1.45
    だよね
    -1.45
     usamos
    -1.45
     accesible
    -1.44
     ją
    -1.43
    POSITIVE LOGITS
    ༀ
    1.67
    €™
    1.62
    They
    1.59
    ｍ
    1.57
    ())))
    1.57
    \_
    1.55
    。"
    1.55
    ي
    1.55
    '
    1.55
    ther
    1.52
    Activations Density 0.017%

    No Known Activations