© 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. 5377
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to proper‐noun place names, especially city names (e.g. “Fort Lauderdale”).

    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
     Deaf
    0.95
     deaf
    0.91
    ات
    0.90
    場合
    0.85
     politically
    0.84
    a
    0.83
     backseat
    0.82
     wheelchair
    0.81
    ୃ
    0.81
     brazen
    0.81
    POSITIVE LOGITS
    ély
    0.74
    ut
    0.74
    ake
    0.70
    Hs
    0.68
    ീതി
    0.67
     прежде
    0.66
    ри
    0.66
    rots
    0.66
     প্রবৃত্ত
    0.66
     thở
    0.64
    Activations Density 0.000%

    No Known Activations