© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12497
    Prev
    Next
    INDEX
    Explanations

    first names followed by last names

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

    The neuron activates on tokens that are full personal names (proper names of people).

    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
    称
    0.26
     the
    0.24
    の
    0.23
     của
    0.23
    =>{
    0.23
    Inicio
    0.23
    セン
    0.22
    ที่
    0.22
    筛
    0.22
    可是
    0.22
    POSITIVE LOGITS
    ᱓
    0.26
    ADIUM
    0.25
    ᱔
    0.24
     WILLIAM
    0.23
     interstices
    0.22
    ೪
    0.22
    ᖇ
    0.22
     MARTIN
    0.22
     entrees
    0.22
     experiential
    0.21
    Activations Density 0.168%

    No Known Activations