© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5970
    Prev
    Next
    INDEX
    Explanations

    definitions or meanings

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

    This neuron responds to dictionary‐entry formatting cues—things like numbered senses, part‐of‐speech tags (adj, n), bracketed or parenthesized labels, figure references, and similar lexical‐definition markers.

    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
     is
    0.58
    ipher
    0.57
    라는
    0.57
    이라는
    0.57
    键
    0.57
     onsite
    0.56
     executed
    0.56
    在于
    0.56
    之
    0.56
    ㅗ
    0.56
    POSITIVE LOGITS
     colloquial
    0.85
     economici
    0.74
     frase
    0.71
     dinheiro
    0.71
     gyak
    0.70
     кг
    0.69
     Türkei
    0.68
     hippie
    0.68
     coppia
    0.67
     чаще
    0.66
    Activations Density 0.007%

    No Known Activations