© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5754
    Prev
    Next
    INDEX
    Explanations

    python web frameworks

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

    The neuron strongly activates on mentions of software library or module names (e.g. Express, connect-mongo, passport, Socket.io) in code-oriented text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    for
    0.73
     phospho
    0.68
    für
    0.68
     inflammatory
    0.67
     augmenter
    0.67
    Bm
    0.64
    Ш
    0.64
     stirrer
    0.63
     accessory
    0.63
     pest
    0.63
    POSITIVE LOGITS
     পড়ুন
    0.80
     Ayrıca
    0.76
    翀
    0.74
     تقریباً
    0.73
     每个
    0.72
     Kỳ
    0.72
    無論
    0.72
     ayrıca
    0.71
     Lào
    0.71
     Macron
    0.71
    Activations Density 0.008%

    No Known Activations