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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7973
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and postpositions

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

    The neuron is highly responsive to Korean (Hangul) 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_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
    ğini
    0.57
    さを
    0.57
    мую
    0.56
     ஒன்றை
    0.55
    片段
    0.55
    টাই
    0.55
    步骤
    0.54
     ؟
    0.54
    了吗
    0.54
     வழங்கு
    0.53
    POSITIVE LOGITS
    にとって
    1.50
    にとっては
    1.45
    에게
    1.32
    한테
    1.10
     számára
    1.06
     પાસે
    1.03
    만의
    1.03
     પાસેથી
    1.01
     විසින්
    0.97
     কর্তৃক
    0.96
    Activations Density 0.021%

    No Known Activations