© 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. 10-GEMMASCOPE-RES-131K
    7. 48506
    Prev
    Next
    INDEX
    Explanations

    wedding and marriage events

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects wedding‐related ceremony actions and announcements—phrases like “set a date,” “save the date,” and “walk down the aisle.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     staffel
    -1.49
    chnung
    -1.44
     ſol
    -1.42
     dring
    -1.41
     dieß
    -1.37
     corriger
    -1.34
     volle
    -1.34
    genodigd
    -1.33
     baden
    -1.31
    actéristi
    -1.30
    POSITIVE LOGITS
     "
    1.51
     and
    1.48
     You
    1.40
     Although
    1.29
     Having
    1.28
     one
    1.28
     Even
    1.27
     Making
    1.22
     may
    1.21
     M
    1.19
    Activations Density 0.031%

    No Known Activations