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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57498
    Prev
    Next
    INDEX
    Explanations

    class/controller namesData duplicationfile headersGUI widgets

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

    The neuron is triggered by C/C++ “#include” header-import lines, i.e. it detects include directives and their quoted or angle-bracketed filenames.

    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
    Ꮞ
    -1.37
     their
    -1.32
     เรา
    -1.28
     景点
    -1.22
    خم
    -1.22
    Lable
    -1.20
     dacă
    -1.19
    SanPham
    -1.19
    Morfo
    -1.16
    ありがたい
    -1.16
    POSITIVE LOGITS
     while
    1.43
    TProtocol
    1.37
     this
    1.33
    ()]);
    1.27
     chanteuse
    1.26
     will
    1.26
    冽
    1.23
    this
    1.21
     ενώ
    1.19
    筵
    1.18
    Activations Density 0.076%

    No Known Activations