© 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. 13009
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly selective for the word “production.”

    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
    6
    1.02
    5
    0.95
    1
    0.94
    4
    0.94
    3
    0.92
    im
    0.88
    2
    0.87
    ox
    0.86
    9
    0.86
    8
    0.84
    POSITIVE LOGITS
     proliferative
    0.87
     いや
    0.82
     connaissez
    0.82
     encuent
    0.81
     quieran
    0.80
     नक्स
    0.80
     けど
    0.79
     elated
    0.78
     prueba
    0.77
     conocer
    0.77
    Activations Density 0.000%

    No Known Activations