© 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. 119771
    Prev
    Next
    INDEX
    Explanations

    connecting with others

    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
     использование
    -2.00
     رائع
    -1.86
    '
    -1.85
     marvelous
    -1.76
     используют
    -1.76
    having
    -1.73
     aprobó
    -1.72
    </h3>
    -1.72
     asegurarse
    -1.71
     unending
    -1.67
    POSITIVE LOGITS
     There
    2.55
     gives
    1.99
     would
    1.95
     лютого
    1.85
     could
    1.76
    釆
    1.68
     ткани
    1.68
     Usually
    1.66
     квітня
    1.66
    abancı
    1.66
    Activations Density 0.010%

    No Known Activations