© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2150
    Prev
    Next
    INDEX
    Explanations

    commercial use or building

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

    The neuron fires on occurrences of the word “commercial” (in any context or casing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "commercial" or "Commercial" in business and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to commercial or industrial contexts, signaling business-related topics and services.

    oai_token-act-pair · gpt-5Triggered 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
    اب
    0.60
     není
    0.59
    ֥
    0.59
     Το
    0.57
    彳
    0.57
    cerr
    0.56
     આ
    0.54
    ipping
    0.54
    Ꮒ
    0.54
    ͈
    0.54
    POSITIVE LOGITS
    Commercial
    1.09
     Commercial
    1.05
     commercial
    1.02
     commercially
    1.00
    commercial
    0.99
     commerciale
    0.95
     commerciali
    0.93
     COMMERCIAL
    0.91
     comerciais
    0.89
     commer
    0.88
    Activations Density 0.212%

    No Known Activations