© 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. 104329
    Prev
    Next
    INDEX
    Explanations

    lux and words containing lux

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

    The neuron activates whenever it encounters the substring “lux” (in any context or word).

    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
    箆
    -3.22
    􀂃
    -3.11
    踽
    -2.92
    繻
    -2.88
    ſelf
    -2.81
    镔
    -2.72
    哢
    -2.69
     despues
    -2.69
    戩
    -2.66
    焌
    -2.66
    POSITIVE LOGITS
    .
    4.47
    ’
    3.95
     has
    2.98
    \
    2.72
     gets
    2.61
    ?"
    2.59
    ]
    2.58
     и
    2.56
     "
    2.53
    暨
    2.53
    Activations Density 0.003%

    No Known Activations