© 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. 3656
    Prev
    Next
    INDEX
    Explanations

    build process and compilation settings

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

    The neuron activates strongly on numeric constants (i.e., integer literals) in code.

    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
     ΤΟ
    -1.13
    あんな
    -0.94
    łania
    -0.94
    あー
    -0.93
    なに
    -0.91
     transacciones
    -0.87
    のもの
    -0.87
    ほら
    -0.87
     ライト
    -0.85
    の作成
    -0.85
    POSITIVE LOGITS
    Manfaat
    1.08
    Karakter
    0.98
    ttää
    0.94
     by
    0.93
    憩
    0.92
    معرفی
    0.91
    javas
    0.90
    捗
    0.90
     there
    0.90
    Baş
    0.88
    Activations Density 0.093%

    No Known Activations