© 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. 22-GEMMASCOPE-RES-131K
    7. 32587
    Prev
    Next
    INDEX
    Explanations

    annual celebrations and events

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

    The neuron detects mentions of anniversaries (e.g. “anniversary” following a number or in a title).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     или
    -2.61
    俛
    -2.53
     are
    -2.48
    
    -2.23
     startling
    -2.22
     decidedly
    -2.17
    泚
    -2.16
     takže
    -2.11
     alguns
    -2.11
     atau
    -2.11
    POSITIVE LOGITS
     of
    3.05
    ↵
    2.03
     sowohl
    1.95
    台南
    1.90
    d
    1.82
     classy
    1.80
    ！（
    1.75
     unrelenting
    1.73
    𝘁
    1.72
     unparalleled
    1.70
    Activations Density 0.004%

    No Known Activations