© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9329
    Prev
    Next
    INDEX
    Explanations

    Pennsylvania locations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of geographic place names—especially “Pennsylvania” and other location names.

    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_31_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
    गुजरात
    0.61
    鹿児島
    0.59
     natoque
    0.57
     jdk
    0.57
    arnataka
    0.56
    曳
    0.55
     Nagpur
    0.55
     Napier
    0.54
     الكويت
    0.54
    莲
    0.54
    POSITIVE LOGITS
     Philadelphia
    2.58
    Philadelphia
    2.53
    Pennsylvania
    2.48
     Philly
    2.45
     Pennsylvania
    2.41
     Phillies
    1.97
     Penn
    1.72
     Phila
    1.72
    Penn
    1.69
     Harrisburg
    1.67
    Activations Density 0.291%

    No Known Activations