© 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. 69291
    Prev
    Next
    INDEX
    Explanations

    Carlos Pinto

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

    The neuron strongly activates on Thai-language day‐of‐week names.

    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
     in
    -2.39
    </h2>
    -2.09
     However
    -1.98
    ")));
    -1.93
     For
    -1.93
     Despite
    -1.91
     Once
    -1.87
    大半
    -1.86
     Ironically
    -1.80
    </em>
    -1.80
    POSITIVE LOGITS
    ’
    2.30
    いろんな
    2.02
    ほんとに
    1.95
    色々と
    1.95
    色んな
    1.92
    𨨏
    1.92
    頑張って
    1.87
    鶿
    1.85
    色々
    1.83
    我們的
    1.80
    Activations Density 0.001%

    No Known Activations