© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49370
    Prev
    Next
    INDEX
    Explanations

    wedding knot

    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
     tuyển
    -0.80
     Sorbonne
    -0.79
    )]);
    -0.77
    Atención
    -0.76
    giène
    -0.76
    γγε
    -0.75
    entrant
    -0.74
     jerry
    -0.73
     convoluted
    -0.73
     lone
    -0.73
    POSITIVE LOGITS
     venue
    2.13
     wedding
    1.95
     weddings
    1.74
     event
    1.65
     venues
    1.54
     ceremony
    1.41
     brides
    1.40
    Venue
    1.37
     Wedding
    1.36
     Venue
    1.34
    Activations Density 0.024%

    No Known Activations