© 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. 93917
    Prev
    Next
    INDEX
    Explanations

    C++ vector

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

    The neuron is keyed to C/C++ include directives for the standard “vector” header (i.e. “#include <vector>”).

    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
     ślub
    -0.78
    prilis
    -0.74
     dictionaries
    -0.73
    ([[
    -0.70
    disposed
    -0.69
    万美元
    -0.69
    막
    -0.66
    Vitals
    -0.66
    /******/
    -0.66
     although
    -0.66
    POSITIVE LOGITS
     vector
    4.41
    vector
    3.86
     vectors
    3.11
     Vector
    3.11
    Vector
    2.97
     вектор
    2.72
    vec
    2.61
     vec
    2.52
    VECTOR
    2.50
     vektor
    2.42
    Activations Density 0.030%

    No Known Activations