© 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. 102958
    Prev
    Next
    INDEX
    Explanations

    options and parameters

    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
    穿搭
    -0.81
     Medford
    -0.78
    мости
    -0.78
    يلي
    -0.78
     Fällen
    -0.78
     toate
    -0.77
    三种
    -0.77
     information
    -0.77
     配
    -0.77
     größeren
    -0.77
    POSITIVE LOGITS
    onchange
    0.99
     are
    0.93
     konto
    0.90
    ('-'
    0.88
    tică
    0.88
    мба
    0.86
    
    0.85
     Vincenzo
    0.85
    = 
    0.85
     vilka
    0.84
    Activations Density 0.059%

    No Known Activations