© 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. 34-GEMMASCOPE-RES-131K
    7. 1676
    Prev
    Next
    INDEX
    Explanations

    LLVM C++ library headers

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

    The neuron is detecting C++ code tokens—especially punctuation and template/type names (e.g. “vector,” “::,” “<,” “>,” “;,” “data,” etc.).

    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
     Lag
    -0.77
    ಿದ
    -0.73
    tego
    -0.72
    gante
    -0.72
    λαι
    -0.71
     Mahar
    -0.71
    PLACE
    -0.69
     قوان
    -0.69
     Seer
    -0.68
    omez
    -0.68
    POSITIVE LOGITS
     allocator
    0.83
    ському
    0.79
    allocator
    0.77
    Allocator
    0.75
    FECT
    0.75
    lished
    0.75
    StatusOK
    0.75
     Alloc
    0.72
    Maine
    0.72
    嗓
    0.71
    Activations Density 0.057%

    No Known Activations