© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72972
    Prev
    Next
    INDEX
    Explanations

    language codes separated by colon

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

    This neuron detects language or locale identifiers—two-letter language codes (optionally with region tags) often followed by colons or underscores.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pág
    -1.13
     azule
    -1.09
     this
    -1.08
     colch
    -1.04
     ortop
    -1.03
    чатку
    -1.02
     Viernes
    -1.00
    
    -1.00
     perca
    -1.00
     navigu
    -1.00
    POSITIVE LOGITS
    1.25
    طريقة
    1.08
     специалисты
    1.05
     шесть
    1.05
     метра
    1.05
     Павел
    1.04
     عددی
    1.03
     Мария
    1.02
     для
    1.02
     тысячи
    1.02
    Activations Density 0.090%

    No Known Activations