© 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. 73765
    Prev
    Next
    INDEX
    Explanations

    XML syntax and structure

    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
     énergétique
    -0.79
    ⚐
    -0.77
    ansha
    -0.74
     verletzt
    -0.74
     chimique
    -0.70
    
    -0.70
    ૅ
    -0.68
    力
    -0.67
     nigger
    -0.67
    moor
    -0.67
    POSITIVE LOGITS
    XmlElement
    0.79
    imakasih
    0.79
     xmlns
    0.77
    薨
    0.77
    Не
    0.76
     licha
    0.75
    ρε
    0.75
    Xml
    0.75
     ELISA
    0.75
     Glaub
    0.75
    Activations Density 0.003%

    No Known Activations