© 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. 11946
    Prev
    Next
    INDEX
    Explanations

    models.Field definition

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

    The neuron activates on sequences of digits with decimal points (e.g. floating‐point numbers and numeric citations).

    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
     cerc
    0.74
     μυ
    0.71
    culas
    0.68
    輿
    0.67
    atinum
    0.67
     lục
    0.67
     analys
    0.66
    mybatis
    0.66
     isotype
    0.66
     oğlu
    0.66
    POSITIVE LOGITS
     सब्सक्राइब
    0.70
    LIKE
    0.68
    早上
    0.66
    忐
    0.66
    RA
    0.64
     %>/
    0.63
    "}
    0.63
    ணிய
    0.63
    死了
    0.62
     दिव्यांग
    0.62
    Activations Density 0.002%

    No Known Activations