© 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. 21830
    Prev
    Next
    INDEX
    Explanations

    System.Runtime code

    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
    _
    -2.08
    aneity
    -1.97
     omfatt
    -1.82
    
    -1.76
     fortfarande
    -1.73
     kän
    -1.67
     sujetos
    -1.65
    他の
    -1.63
     coloridos
    -1.63
    ere
    -1.62
    POSITIVE LOGITS
     ");
    1.77
    ⸥
    1.62
     comanda
    1.55
    čním
    1.55
    pendente
    1.55
     femminile
    1.48
     soggior
    1.47
    lindo
    1.45
    1
    1.45
     bici
    1.44
    Activations Density 0.002%

    No Known Activations