© 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. 45208
    Prev
    Next
    INDEX
    Explanations

    C++ standard library containers

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

    The neuron is tuned to detect numeric literal tokens (i.e. standalone numbers) in code.

    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
    arraycopy
    -0.89
    喀
    -0.75
    ÇÕES
    -0.74
    orative
    -0.74
     Hamza
    -0.71
    ropia
    -0.71
    cdots
    -0.70
     Hutchinson
    -0.69
    Whoa
    -0.69
    edia
    -0.67
    POSITIVE LOGITS
     vector
    2.75
    vector
    2.59
     string
    1.79
    string
    1.73
     pair
    1.55
     vectors
    1.52
     map
    1.45
    pair
    1.44
    map
    1.34
     вектор
    1.27
    Activations Density 0.080%

    No Known Activations