© 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. 15765
    Prev
    Next
    INDEX
    Explanations

    referring to previous mention

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

    The neuron detects mathematical or quantitative estimation terms (e.g. references to sampling, graphs, curves, axes, counts, and measurement-related words).

    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
     них
    0.71
     آنها
    0.68
     बाती
    0.67
    نساء
    0.64
    velles
    0.64
     ними
    0.63
     тях
    0.62
    賈
    0.61
    InEx
    0.61
    ských
    0.59
    POSITIVE LOGITS
     aforementioned
    1.04
    上述
    0.88
     aforesaid
    0.88
     mentioned
    0.83
    上記の
    0.76
     above
    0.75
     the
    0.74
     *
    0.73
     mencionado
    0.72
     tadi
    0.71
    Activations Density 2.276%

    No Known Activations