© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49158
    Prev
    Next
    INDEX
    Explanations

    just + qualifier

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

    The neuron strongly activates on the adverb “just” (and similar emphasis/filler adverbs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    üe
    -0.83
    脈
    -0.79
     rapporter
    -0.79
    야
    -0.79
    ksjoner
    -0.77
    च
    -0.77
     membri
    -0.76
    ae
    -0.76
    Fluor
    -0.75
     MARIA
    -0.75
    POSITIVE LOGITS
     before
    0.88
     превос
    0.87
     about
    0.84
     aswell
    0.79
     to
    0.79
    Just
    0.79
     for
    0.77
    ậ
    0.76
    Sometimes
    0.76
    Хорошо
    0.75
    Activations Density 0.013%

    No Known Activations