© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38488
    Prev
    Next
    INDEX
    Explanations

    Happy holiday greetings and birthdays

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

    The neuron activates on celebratory greeting phrases—especially “Happy” or “Merry” followed by holidays, birthdays, or similar occasions.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     you
    -1.74
     there
    -1.55
     it
    -1.55
    〤
    -1.50
    đại
    -1.47
     beaucoup
    -1.44
    丷
    -1.43
     armazen
    -1.36
    は無
    -1.34
     almacen
    -1.30
    POSITIVE LOGITS
    Still
    1.66
    They
    1.51
    4
    1.50
    </b>
    1.45
     time
    1.42
    Just
    1.41
    Despite
    1.40
    Currently
    1.40
    These
    1.30
    ','
    1.30
    Activations Density 0.009%

    No Known Activations