© 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. 12595
    Prev
    Next
    INDEX
    Explanations

    specific actions or concepts

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

    The neuron responds strongly to countable entities—especially plural nouns that enumerate items or elements in a 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
    有两种
    0.64
    最后一个
    0.63
    这类
    0.62
    自从
    0.58
     जिसने
    0.58
    有两个
    0.57
     harboring
    0.57
    在这种
    0.57
    我现在
    0.55
    只有
    0.54
    POSITIVE LOGITS
     etc
    0.73
     وغیرہ
    0.67
    そして
    0.63
    etc
    0.62
     वगैरह
    0.61
    ต่างๆ
    0.58
     тощо
    0.57
     agus
    0.57
     প্রমুখ
    0.57
     इत्यादि
    0.56
    Activations Density 0.446%

    No Known Activations