© 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. 69245
    Prev
    Next
    INDEX
    Explanations

    Wes names and FTSE

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

    The neuron specifically detects occurrences of the string “Wes,” as in the proper name Wes.

    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
    ه
    -2.67
    髕
    -2.55
    洐
    -2.53
    ان
    -2.52
    ↑↑↑</
    -2.52
    »),
    -2.48
    谔
    -2.45
    »)
    -2.45
     който
    -2.41
    两年
    -2.39
    POSITIVE LOGITS
    y
    3.05
    ଃ
    2.77
    癀
    2.48
     один
    2.47
    笮
    2.45
     are
    2.44
    我们
    2.41
    ть
    2.41
    酹
    2.41
    菝
    2.36
    Activations Density 0.001%

    No Known Activations