© 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. 5858
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on the very first real content word in each new text segment—i.e. it marks the beginning of a 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
    rather
    0.84
    诒
    0.80
    tiene
    0.79
    r
    0.79
    rset
    0.78
    ride
    0.78
     generalmente
    0.77
    incontro
    0.77
    Height
    0.76
    s
    0.76
    POSITIVE LOGITS
     Ağustos
    0.79
     consonants
    0.77
     Admittedly
    0.73
     besoin
    0.72
     Çocuk
    0.72
     colds
    0.71
     oiseaux
    0.71
    сть
    0.70
    無需
    0.70
     Dès
    0.69
    Activations Density 0.000%

    No Known Activations