© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9142
    Prev
    Next
    INDEX
    Explanations

    attribution and licensing

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

    The neuron fires on text indicating Creative Commons licensing statements (e.g. “licensed under Creative Commons Attribution-…”).

    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
     성능
    0.61
    groupBox
    0.60
    绩效
    0.59
     ಖರೀ
    0.59
    сів
    0.59
    simulator
    0.57
    🥱
    0.57
    🛎
    0.56
     பள்ளத்தா
    0.55
     JVM
    0.55
    POSITIVE LOGITS
    creativecommons
    1.22
     Attribution
    1.15
     Creative
    0.97
     attribution
    0.96
    Creative
    0.92
    attribution
    0.92
     CC
    0.87
    licenses
    0.83
     licence
    0.79
     licences
    0.79
    Activations Density 0.074%

    No Known Activations