© 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. 58037
    Prev
    Next
    INDEX
    Explanations

    Jubilee, Jamboree, Centenary

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

    The neuron fires on capitalized multi‐letter tokens—i.e. proper names and other named‐entity words.

    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
    
    -3.02
    俛
    -3.00
    咴
    -2.94
     vhod
    -2.83
     zdroj
    -2.69
     tématu
    -2.67
    気味
    -2.61
     установка
    -2.56
    呿
    -2.53
    ykjav
    -2.52
    POSITIVE LOGITS
    After
    2.92
    All
    2.88
    While
    2.72
    Since
    2.70
    e
    2.66
    Despite
    2.58
    Although
    2.56
    s
    2.48
    From
    2.48
    If
    2.45
    Activations Density 0.001%

    No Known Activations