© 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. 6772
    Prev
    Next
    INDEX
    Explanations

    Halloween celebration

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

    The neuron activates specifically on occurrences of the word “Halloween.”

    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
    ’
    -3.14
     \
    -3.05
     This
    -2.94
    2
    -2.73
    乆
    -2.66
    s
    -2.64
     When
    -2.41
     -
    -2.39
    This
    -2.38
    少ない
    -2.38
    POSITIVE LOGITS
    Ꭳ
    3.06
    鷓
    3.03
    胧
    3.02
    姈
    2.95
    鲽
    2.94
    ⽌
    2.78
    垟
    2.64
    鷙
    2.61
    垸
    2.61
    鰾
    2.56
    Activations Density 0.002%

    No Known Activations