© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7536
    Prev
    Next
    INDEX
    Explanations

    texts about legal matters

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

    The neuron strongly activates on product‐oriented metadata and promotional labels (e.g. brand names, product codes, category or tag listings).

    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
     Monate
    0.60
     messo
    0.58
     engulfed
    0.57
     cơn
    0.56
     ​
    0.55
    Kako
    0.55
     sogen
    0.55
     freaking
    0.54
     ผู้
    0.54
     phenomenal
    0.54
    POSITIVE LOGITS
    读者
    0.52
    uene
    0.51
    珪
    0.51
    पीएससी
    0.49
     substituents
    0.49
    arza
    0.49
     salarié
    0.49
    arre
    0.48
     tarjetas
    0.48
    пети
    0.47
    Activations Density 7.090%

    No Known Activations