© 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. 12224
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on the indefinite articles “a” and “an” preceding a noun or noun phrase.

    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
    на
    0.85
    一种
    0.84
     correctes
    0.82
    cita
    0.82
    ls
    0.81
    lots
    0.81
    ਨ
    0.81
    有點
    0.79
     understandable
    0.79
     multiplets
    0.78
    POSITIVE LOGITS
     bygone
    0.92
     woman
    0.91
     poultry
    0.78
     группа
    0.77
     گروه
    0.75
     través
    0.73
     अन्य
    0.73
     businesswoman
    0.73
     husband
    0.72
     clergyman
    0.72
    Activations Density 0.323%

    No Known Activations