© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98220
    Prev
    Next
    INDEX
    Explanations

    Q followed by colon

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

    The neuron activates on C/C++ header‐file include tokens (the “.h” in #include statements).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     mientras
    -0.84
    dstuk
    -0.84
    RTSN
    -0.79
    RTCF
    -0.74
    Fd
    -0.74
    DispatchQueue
    -0.70
    chak
    -0.69
     vux
    -0.69
     while
    -0.69
    Fernando
    -0.69
    POSITIVE LOGITS
    paramref
    0.85
    bezpiecz
    0.83
     Sélection
    0.82
    ⇡
    0.81
     gefragt
    0.81
    жня
    0.80
    RAG
    0.78
     avert
    0.78
    rety
    0.78
     turquesa
    0.77
    Activations Density 0.000%

    No Known Activations