© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44554
    Prev
    Next
    INDEX
    Explanations

    marriage and wedding events

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

    The neuron fires on words and phrases referring to marriage or weddings (e.g., married, wedding, tying the knot).

    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
     is
    -2.06
    歺
    -1.52
    forKey
    -1.45
    訁
    -1.43
     PAST
    -1.42
    5
    -1.42
    melidir
    -1.41
    所有人
    -1.35
     каждого
    -1.35
    Says
    -1.34
    POSITIVE LOGITS
     on
    2.09
     two
    1.80
     July
    1.77
     September
    1.66
     another
    1.60
     what
    1.55
     one
    1.52
     probably
    1.50
     shortly
    1.48
     Although
    1.48
    Activations Density 0.030%

    No Known Activations