© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15749
    Prev
    Next
    INDEX
    Explanations

    performance related to improvement or review

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

    The neuron fires on occurrences of the noun “performance.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सर्वेक्षण
    0.67
     Pobl
    0.66
     ჭ
    0.65
    ूरत
    0.64
    arium
    0.63
    tor
    0.62
     dys
    0.61
    sce
    0.61
    ة
    0.61
    rette
    0.61
    POSITIVE LOGITS
    performance
    1.16
    Performance
    1.16
    パフォーマンス
    1.16
     performance
    1.16
     Performance
    1.15
    性能
    1.07
     PERFORMANCE
    1.03
     performances
    0.93
     kinerja
    0.92
     Performances
    0.91
    Activations Density 0.089%

    No Known Activations