© 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. 75288
    Prev
    Next
    INDEX
    Explanations

    illumin and illumination

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

    The neuron strongly activates on the character sequence “illumin” (e.g. in “illumination,” “illuminator,” “Illuminations”).

    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
    It
    -3.28
    In
    -3.00
    If
    -2.97
    You
    -2.88
    小孩子
    -2.69
     '
    -2.66
     he
    -2.66
    -
    -2.61
    This
    -2.56
    其他
    -2.53
    POSITIVE LOGITS
    ଝ
    3.09
    髫
    2.78
    柃
    2.73
    躝
    2.69
    璈
    2.64
    ⡑
    2.50
     orale
    2.50
    驺
    2.45
    慊
    2.39
    猹
    2.38
    Activations Density 0.003%

    No Known Activations