© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6520
    Prev
    Next
    INDEX
    Explanations

    regional slang and dialects

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

    The neuron detects content describing cultural or traditional topics (e.g. customs, foods, music, countries) often in the context of travel or exploration.

    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
     positron
    0.69
    铂
    0.63
     cisplatin
    0.63
     valut
    0.62
     ambitious
    0.61
     spoiler
    0.60
     aspart
    0.60
     SII
    0.60
     ZF
    0.60
    ኬ
    0.60
    POSITIVE LOGITS
     traditions
    2.19
     Traditions
    2.13
     tradiciones
    2.13
     folklor
    2.08
     전통
    2.03
     tradición
    2.00
    伝統
    1.99
     tradition
    1.97
     cultural
    1.95
    文化
    1.91
    Activations Density 1.082%

    No Known Activations