© 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. 58509
    Prev
    Next
    INDEX
    Explanations

    either ... or construction

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

    This neuron fires on the discourse marker “either,” especially when it introduces an “either … or” construction.

    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
     &
    -3.06
    </b>
    -2.63
    na
    -2.22
    絎
    -2.16
     leur
    -2.14
     {
    -2.11
    to
    -1.97
     estadounid
    -1.96
     consequent
    -1.85
    葎
    -1.85
    POSITIVE LOGITS
    </h3>
    3.09
    owm
    2.06
    描写
    2.05
     implique
    2.02
     speziellen
    1.92
     semejante
    1.91
    lanır
    1.88
    玧
    1.88
    řit
    1.87
    
    1.84
    Activations Density 0.019%

    No Known Activations