© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111747
    Prev
    Next
    INDEX
    Explanations

    code generator

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

    auto-generated code files with boilerplate headers and copyright notices.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on boilerplate “generated by” comments naming code‐generation tools.

    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
     they
    -1.95
    是用
    -1.51
    ис
    -1.48
    潯
    -1.48
    是什么意思
    -1.47
    在我的
    -1.46
     kutumia
    -1.46
    ！）
    -1.46
    开始
    -1.45
    m
    -1.43
    POSITIVE LOGITS
     to
    1.80
    瑒
    1.63
     Otras
    1.63
     Algunas
    1.53
     problemy
    1.45
     Muchos
    1.42
     Algunos
    1.42
     Большая
    1.38
    auda
    1.35
    ৄ
    1.34
    Activations Density 0.001%

    No Known Activations