© 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. 22-GEMMASCOPE-RES-131K
    7. 128912
    Prev
    Next
    INDEX
    Explanations

    This neuron detects the discourse filler “just.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    just followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -1.43
    PENDAHULUAN
    -1.35
    zapatos
    -1.34
    loài
    -1.20
    sandalia
    -1.20
    álise
    -1.18
    unitOfWork
    -1.18
     considération
    -1.16
    ettbewer
    -1.12
    觏
    -1.12
    POSITIVE LOGITS
    B
    1.28
    M
    1.19
             
    1.17
           
    1.17
    I
    1.16
                
    1.15
    过程
    1.13
    ed
    1.13
    G
    1.12
               
    1.11
    Activations Density 0.025%

    No Known Activations