© 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. 34-GEMMASCOPE-RES-131K
    7. 79438
    Prev
    Next
    INDEX
    Explanations

    Bung- / Bong- / Tung- prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Chao
    -0.84
     разно
    -0.75
    forChild
    -0.75
    ьи
    -0.73
     Chao
    -0.73
    reportError
    -0.71
     кон
    -0.70
     veloce
    -0.70
    Chandigarh
    -0.69
    Polynomial
    -0.69
    POSITIVE LOGITS
     Bung
    0.86
     زرد
    0.79
    ecord
    0.77
    ANTE
    0.74
    repar
    0.73
    timiento
    0.72
    Bung
    0.70
     bung
    0.69
    ardt
    0.69
     сні
    0.69
    Activations Density 0.013%

    No Known Activations