© 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. 14181
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the very first substantive token of each new text block, i.e. it detects the start of a new “document” or section.

    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
    ut
    0.77
    گر
    0.75
     els
    0.73
    0
    0.72
     accad
    0.72
    やっと
    0.71
     ressources
    0.71
    ahar
    0.68
    ats
    0.68
     capitalize
    0.67
    POSITIVE LOGITS
    sman
    0.92
    speople
    0.83
    south
    0.82
    鰯
    0.82
     बटा
    0.81
    cellulose
    0.79
     लिपि
    0.77
     Serviço
    0.77
    CustomerID
    0.76
    cust
    0.76
    Activations Density 0.000%

    No Known Activations