© 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. 67359
    Prev
    Next
    INDEX
    Explanations

    conversational interjections

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

    This neuron spots emphatic interjections or discourse markers (e.g., “Oh,” “OK,” “Hey,” “Yes”) used to express emotion or transition.

    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
     as
    -2.55
     or
    -2.52
     all
    -2.16
     some
    -2.09
     only
    -2.03
     any
    -1.95
     one
    -1.93
     this
    -1.92
     not
    -1.92
     new
    -1.91
    POSITIVE LOGITS
     penser
    1.92
    commonly
    1.91
    particularly
    1.89
     stary
    1.84
     maniere
    1.84
     incluse
    1.83
    
    1.81
    骉
    1.80
    蟊
    1.80
     nowe
    1.77
    Activations Density 0.061%

    No Known Activations