© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12829
    Prev
    Next
    INDEX
    Explanations

    Okay, I'm ready!

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

    The neuron detects professional bio or resume–style self-introductions and service pitches (e.g. “I am a writer and editor with…,” “Receive free website copywriting quotes,” “Professionally, I am a writer and editor…”).

    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_24_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
     Když
    0.67
     있는데
    0.66
    课堂
    0.64
    尴尬
    0.63
    出现了
    0.63
    žila
    0.63
    盒子
    0.62
     있지만
    0.61
    샀
    0.61
     parfois
    0.60
    POSITIVE LOGITS
     предлага
    0.93
     услуг
    0.89
     можете
    0.87
     Capabilities
    0.86
    capability
    0.83
     Fiverr
    0.82
     প্রস্তাব
    0.80
     работаю
    0.80
     готовы
    0.79
     freelancer
    0.78
    Activations Density 0.325%

    No Known Activations