© 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. 87030
    Prev
    Next
    INDEX
    Explanations

    alternative choices or methods

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

    This neuron specifically responds to occurrences of the word “alternative.”

    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
    这一幕
    -1.45
     zarówno
    -1.42
    普通人
    -1.40
    灕
    -1.38
    Pengertian
    -1.38
     Володи
    -1.37
     sogen
    -1.35
     neuem
    -1.33
    人たち
    -1.29
     céramique
    -1.27
    POSITIVE LOGITS
    。
    1.69
     газа
    1.46
    alternative
    1.43
    мання
    1.35
     ++)
    1.34
     затем
    1.34
     you
    1.34
    蔟
    1.30
     conclusão
    1.30
     know
    1.27
    Activations Density 0.059%

    No Known Activations