© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10529
    Prev
    Next
    INDEX
    Explanations

    demonstrative demonstrative phrases

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

    The neuron fires strongly on content-bearing words (nouns, verbs, and key adjectives) rather than on function words or punctuation.

    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_31_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
     	i
    0.96
     इन्होंने
    0.86
     questi
    0.79
     इन्हे
    0.78
     ovako
    0.77
     이렇게
    0.77
     इन्हें
    0.76
     इनके
    0.75
     Здесь
    0.73
     இவற்றை
    0.73
    POSITIVE LOGITS
    那個
    3.69
    那个
    3.66
    那
    3.63
    That
    3.61
     THAT
    3.56
     那
    3.41
     That
    3.34
     đó
    3.22
    那是
    3.19
    THAT
    3.16
    Activations Density 3.198%

    No Known Activations