© 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. 86037
    Prev
    Next
    INDEX
    Explanations

    schedule an appointment or activity

    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
     überprüft
    -1.85
     universitario
    -1.66
     Garantía
    -1.61
     Obrigado
    -1.61
     -¿
    -1.59
     gemessen
    -1.59
    蘼
    -1.59
     SOBRE
    -1.56
     pertence
    -1.55
    
    -1.52
    POSITIVE LOGITS
     for
    1.87
     an
    1.71
    in
    1.70
    li
    1.70
     any
    1.67
     a
    1.66
    </h3>
    1.59
     more
    1.56
    1.52
     or
    1.50
    Activations Density 0.013%

    No Known Activations