© 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. 16105
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for structured metadata and list-heading tokens—especially dates, numbers, and section/segmentation headings in the document.

    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
    ために
    1.09
     Riva
    0.98
     Jiří
    0.91
    ための
    0.89
    יות
    0.89
     Михаил
    0.88
    }}}-\
    0.88
    ק
    0.88
    ภาษา
    0.88
     ドライバー
    0.88
    POSITIVE LOGITS
    /*
    0.88
    *{
    0.77
     inilah
    0.74
    è
    0.74
    {
    0.73
     dette
    0.72
    घाडी
    0.71
     montre
    0.71
     couleurs
    0.71
     voici
    0.71
    Activations Density 0.000%

    No Known Activations