© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98976
    Prev
    Next
    INDEX
    Explanations

    just followed by verbs

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

    The neuron fires strongly on the filler/discourse particle “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
     extremely
    -1.93
     illustratie
    -1.89
     bancaria
    -1.86
     insanely
    -1.84
     mediocre
    -1.83
     gustaMe
    -1.82
    凄く
    -1.81
    蚡
    -1.80
    filtre
    -1.80
     amazingly
    -1.79
    POSITIVE LOGITS
     From
    2.06
     makes
    2.03
     took
    1.98
     gives
    1.96
     did
    1.95
    嗚
    1.91
     if
    1.85
     gave
    1.84
    when
    1.84
     When
    1.78
    Activations Density 0.032%

    No Known Activations