© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15178
    Prev
    Next
    INDEX
    Explanations

    creation agent (by)

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

    The neuron fires on words that credit or attribute creation, production, or authorship (e.g., “created,” “written,” “produced,” “work,” “contributions”).

    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
    ᱮ
    0.91
    त्र
    0.90
    ၈
    0.86
    ᱗
    0.85
    ᱕
    0.83
    ৬
    0.82
    ৭
    0.80
    ၆
    0.80
    ᱘
    0.80
    ᱔
    0.80
    POSITIVE LOGITS
     oleh
    1.68
     by
    1.39
     توسط
    1.29
    โดย
    1.24
     بواسطة
    1.11
    ByUser
    1.03
     tarafından
    1.02
    由
    1.02
     bởi
    0.99
     către
    0.99
    Activations Density 0.731%

    No Known Activations