© 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. 9556
    Prev
    Next
    INDEX
    Explanations

    Romanian nationality or language

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

    The neuron fires on technical documentation or product‐feature descriptions—i.e. passages listing software capabilities and instructions.

    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
    渀
    0.77
     Aztecs
    0.74
    奚
    0.73
    Indians
    0.70
    ਟਰ
    0.69
    岭
    0.67
    盅
    0.67
    喙
    0.66
     psyched
    0.65
    达
    0.64
    POSITIVE LOGITS
     Romanian
    2.20
     Romania
    1.98
     Bucharest
    1.97
     Bucure
    1.95
     România
    1.86
     Cluj
    1.84
    Romania
    1.78
     Bă
    1.34
     Ruman
    1.32
     Ș
    1.31
    Activations Density 0.077%

    No Known Activations