© 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. 47218
    Prev
    Next
    INDEX
    Explanations

    Go Big, Shuttler, Chage

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

    The neuron strongly activates on occurrences of the word “assembly,” especially in C# attribute blocks declaring assembly metadata.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Avez
    -0.87
     this
    -0.81
    syn
    -0.78
     ★★★
    -0.77
    fuck
    -0.76
     ★★★★
    -0.75
     they
    -0.75
     russe
    -0.75
    taxa
    -0.75
    íra
    -0.74
    POSITIVE LOGITS
    มัน
    0.81
    GUY
    0.81
    Guy
    0.74
    Затем
    0.73
     perlahan
    0.73
     грамм
    0.71
    oldo
    0.70
    となる
    0.69
    人都
    0.69
     menunjukkan
    0.68
    Activations Density 0.000%

    No Known Activations