© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72816
    Prev
    Next
    INDEX
    Explanations

    just + word

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

    The neuron is a strong detector of the filler/hedging adverb “just.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     who
    -1.57
     is
    -1.52
     where
    -1.49
     again
    -1.40
     if
    -1.36
    &#
    -1.35
     &
    -1.32
     or
    -1.30
    li
    -1.27
     it
    -1.27
    POSITIVE LOGITS
     員
    1.63
     групи
    1.48
     Empieza
    1.48
     acert
    1.46
     méda
    1.45
     découvrez
    1.42
     Appears
    1.41
     young
    1.34
     Fácil
    1.34
     erlä
    1.33
    Activations Density 0.027%

    No Known Activations