© 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. 10317
    Prev
    Next
    INDEX
    Explanations

    di words

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

    The neuron is activated by tokens that begin with the letter sequence “di” (e.g. Di-, diablo, diminished, diclofenac).

    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
    HAEL
    0.64
     mene
    0.62
     Inflammation
    0.60
    够
    0.60
    媚
    0.54
     Muscle
    0.53
     salient
    0.53
    ட்டார்
    0.53
     നിറഞ്ഞ
    0.53
    ति
    0.52
    POSITIVE LOGITS
     ди
    0.76
    ichlet
    0.75
     डाइ
    0.70
     डाय
    0.70
     ディ
    0.66
     Ді
    0.65
     Dijk
    0.64
     디
    0.63
    eresis
    0.63
     দি
    0.62
    Activations Density 0.369%

    No Known Activations