© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2276
    Prev
    Next
    INDEX
    Explanations

    conjunctions and sentence connectors

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

    This neuron fires on passages of non-English (foreign) language text.

    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
     satu
    0.55
     secara
    0.52
     неко
    0.50
     bergerak
    0.50
     zwró
    0.50
     auftreten
    0.50
    Ꭻ
    0.50
    ＮＡＮＡ
    0.49
     самостоятельно
    0.49
    ۱۹
    0.49
    POSITIVE LOGITS
     Và
    0.77
     Nhưng
    0.69
     Fakat
    0.64
     Empres
    0.59
     Porém
    0.59
     대신
    0.58
     Daarna
    0.57
     만
    0.55
    며
    0.55
     Mình
    0.55
    Activations Density 0.000%

    No Known Activations