© 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. 14059
    Prev
    Next
    INDEX
    Explanations

    immediately followed by diving

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

    The main thing this neuron does is detect tokens in legal‐notice sections, especially trademarks, copyrights, and publication‐origin disclaimers.

    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
     وعلى
    0.82
     М
    0.79
    ಿಯಾಗಿ
    0.79
    yczy
    0.78
     satisfies
    0.77
     secures
    0.74
    이기
    0.73
    ться
    0.72
     settlements
    0.71
    ことができる
    0.70
    POSITIVE LOGITS
    Universität
    0.80
    Instit
    0.80
    COMMAND
    0.79
    मंद
    0.76
    Swami
    0.73
    llam
    0.73
    ➥
    0.73
    th
    0.73
    EST
    0.73
    deprecated
    0.72
    Activations Density 0.001%

    No Known Activations