Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7665
    Prev
    Next
    INDEX
    Explanations

    marriage and weddings

    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
     neque
    -0.98
    ॐ
    -0.95
    үү
    -0.94
    -------
    -0.91
    рѣ
    -0.85
    нете
    -0.84
    PHPExcel
    -0.84
    urato
    -0.83
     girly
    -0.82
    нера
    -0.81
    POSITIVE LOGITS
     marriage
    2.80
    Marriage
    2.20
     Marriage
    2.19
     marriages
    2.02
    marriage
    1.97
     divorce
    1.95
     couples
    1.90
     married
    1.78
     wedding
    1.76
     marital
    1.56
    Activations Density 0.030%

    No Known Activations