© 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. 39154
    Prev
    Next
    INDEX
    Explanations

    C++ types and headers

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

    The neuron fires on C++ type names qualified by a namespace or template (e.g. “std::string,” “std::vector<…>,” or other scoped identifiers).

    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
     and
    -1.97
    lgari
    -1.81
    
    -1.80
     traktor
    -1.60
    farers
    -1.59
     panier
    -1.58
     rapor
    -1.57
    鶿
    -1.55
    umers
    -1.54
     merci
    -1.52
    POSITIVE LOGITS
     of
    2.14
     '
    1.80
     that
    1.79
     who
    1.74
     will
    1.67
     can
    1.66
     lack
    1.60
    들의
    1.57
     embora
    1.56
    It
    1.55
    Activations Density 0.008%

    No Known Activations