© 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. 10-GEMMASCOPE-RES-131K
    7. 61327
    Prev
    Next
    INDEX
    Explanations

    Kivy, Uno, fuse, Quick

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

    The neuron fires on occurrences of specific technology or library/framework names (e.g. “kivy,” “Fuse,” “HaxeFlixel,” “Quick,” “Uno”).

    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
     indiquer
    -1.82
    IGRATION
    -1.77
    镠
    -1.73
    sukienka
    -1.70
     místo
    -1.67
    '
    -1.67
    kurtka
    -1.58
    Kita
    -1.56
     groote
    -1.55
     dovuto
    -1.55
    POSITIVE LOGITS
     of
    1.84
    This
    1.82
    2
    1.66
    8
    1.52
     following
    1.51
    you
    1.47
    M
    1.40
    {
    1.40
    this
    1.38
    s
    1.38
    Activations Density 0.003%

    No Known Activations