© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58479
    Prev
    Next
    INDEX
    Explanations

    just a/an/the

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

    The neuron strongly lights up on the filler/hedging word “just” (and to a lesser extent on simple function words like “a”).

    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
    壜
    -1.77
    nadequate
    -1.73
    
    -1.66
    vermectin
    -1.66
    leyin
    -1.64
    őle
    -1.63
     hva
    -1.63
    ftar
    -1.63
    荜
    -1.63
    unuz
    -1.61
    POSITIVE LOGITS
     a
    2.13
     to
    2.09
     jedynie
    1.73
     only
    1.65
    only
    1.64
    lo
    1.62
    where
    1.61
    :
    1.56
     Now
    1.55
     apenas
    1.52
    Activations Density 0.017%

    No Known Activations