© 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. 14307
    Prev
    Next
    INDEX
    Explanations

    just followed by phrase

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

    This neuron activates on occurrences of the filler/modifier word “just.”

    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
     лишь
    1.10
     Appellant
    0.92
    р
    0.90
    きて
    0.85
    ほん
    0.84
    で
    0.84
    また
    0.83
     그냥
    0.83
    この
    0.81
    о
    0.81
    POSITIVE LOGITS
     oraz
    0.75
     sekä
    0.73
     serta
    0.72
     samt
    0.70
     valamint
    0.70
    गतान
    0.67
    ים
    0.66
     embora
    0.66
    Compar
    0.64
    如图
    0.64
    Activations Density 0.016%

    No Known Activations