© 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. 58333
    Prev
    Next
    INDEX
    Explanations

    lunch and its contexts

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

    The neuron specifically detects occurrences of the word “lunch” (in any context or capitalization).

    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
    ญี่ป
    -3.64
    ꯳
    -3.09
    栳
    -2.75
     белого
    -2.70
    lgari
    -2.67
    acaktır
    -2.58
    𐀀
    -2.56
    鲧
    -2.42
    ें
    -2.41
    澇
    -2.41
    POSITIVE LOGITS
    h
    3.45
    o
    2.98
    al
    2.91
     annuel
    2.56
    ing
    2.50
     n
    2.39
     [
    2.38
    b
    2.28
    .
    2.28
     appla
    2.23
    Activations Density 0.008%

    No Known Activations