© 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. 4640
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on specific named entities—particularly geographic place names (cities, countries, etc.).

    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
    c
    0.71
    Beim
    0.70
    modelo
    0.69
    markdown
    0.67
    model
    0.67
    owl
    0.67
    ה
    0.66
    remove
    0.66
    ک
    0.66
    半
    0.66
    POSITIVE LOGITS
     localities
    0.72
     arrears
    0.71
     condivid
    0.71
     불구하고
    0.71
     pergunt
    0.70
     questione
    0.70
     وفي
    0.70
     городах
    0.70
     cuestión
    0.70
     ‘’
    0.70
    Activations Density 0.000%

    No Known Activations