© 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. 34-GEMMASCOPE-RES-131K
    7. 83460
    Prev
    Next
    INDEX
    Explanations

    scientific notation and symbols

    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_34/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
           
    -0.92
         
    -0.81
               
    -0.79
    底下
    -0.77
     Weiden
    -0.77
    coltà
    -0.73
    odios
    -0.73
        
    -0.71
     stere
    -0.71
    обла
    -0.71
    POSITIVE LOGITS
    ennung
    0.83
    viele
    0.82
    möglich
    0.82
    новение
    0.81
    lowed
    0.80
    Föld
    0.79
    叕
    0.78
    🕉
    0.77
     关
    0.77
     ?>/
    0.77
    Activations Density 0.001%

    No Known Activations