© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103447
    Prev
    Next
    INDEX
    Explanations

    and or after

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

    The neuron fires on coordinating conjunctions (e.g., “and,” “or”) that join clauses or list items.

    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
    -1.45
    ↵↵
    -1.44
     такі
    -1.41
     усі
    -1.20
     सकती
    -1.20
     Throughout
    -1.20
     state
    -1.19
     people
    -1.18
    im
    -1.17
    部長
    -1.16
    POSITIVE LOGITS
     a
    1.76
    ValueStyle
    1.56
    粜
    1.40
     legenda
    1.39
    ␮
    1.39
     dislike
    1.38
    фы
    1.32
     viven
    1.31
     caricatura
    1.31
     Австра
    1.30
    Activations Density 0.053%

    No Known Activations