© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60308
    Prev
    Next
    INDEX
    Explanations

    names containing "wen"

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

    The neuron strongly activates on any occurrence of the character sequence “wen,” whether as part of a proper name or within other words.

    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
    Ꮵ
    -2.95
     vorige
    -2.73
    鸲
    -2.66
     použití
    -2.61
     préstamo
    -2.59
     gustado
    -2.56
    グルト
    -2.56
     丁目
    -2.56
    ſſel
    -2.56
     farben
    -2.55
    POSITIVE LOGITS
    .
    3.09
     Then
    2.98
    \
    2.77
    *
    2.77
     However
    2.73
     Können
    2.66
    ].
    2.56
    ar
    2.48
    `
    2.38
    做的
    2.36
    Activations Density 0.003%

    No Known Activations