© 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. 10912
    Prev
    Next
    INDEX
    Explanations

    creative writing and innovation

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

    The neuron fires on occurrences of the word “creative” (and its close form “creativity”).

    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
    데이터
    0.96
    вки
    0.91
    bases
    0.89
    laştır
    0.89
    來到
    0.88
    и
    0.87
     وحتى
    0.86
    разде
    0.84
    к
    0.83
    ти
    0.82
    POSITIVE LOGITS
     creativity
    1.34
     kreativ
    1.25
     Creativity
    1.18
     Kreat
    1.13
    Creative
    1.10
     innovate
    1.08
     innovator
    1.04
     kreat
    1.03
    創意
    1.02
     inventors
    1.00
    Activations Density 0.282%

    No Known Activations