© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66528
    Prev
    Next
    INDEX
    Explanations

    some X, some Y

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

    This neuron detects indefinite-quantity determiners—especially occurrences of “some.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ledad
    -1.27
     sánh
    -1.09
    bní
    -1.08
     dekol
    -1.05
    laria
    -1.04
     sudadera
    -1.03
    nable
    -1.02
    ún
    -1.02
     nhat
    -1.01
    lifier
    -0.98
    POSITIVE LOGITS
     even
    2.28
    甚至
    1.84
     حتی
    1.81
     даже
    1.77
     sogar
    1.77
     dokonce
    1.69
     nawet
    1.63
    even
    1.55
     bahkan
    1.55
     incluso
    1.49
    Activations Density 0.049%

    No Known Activations