© 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. 10-GEMMASCOPE-RES-131K
    7. 39422
    Prev
    Next
    INDEX
    Explanations

    indefinite article followed by noun

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

    The neuron strongly activates on the standalone indefinite article “a.”

    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
    </em>
    -1.70
     diferentes
    -1.48
    ↵
    -1.44
    を発表
    -1.40
    essoal
    -1.38
    ##
    -1.35
     terá
    -1.31
     ſhould
    -1.30
     the
    -1.27
     each
    -1.26
    POSITIVE LOGITS
     who
    2.92
     яка
    1.56
    ᐕ
    1.51
     young
    1.47
     those
    1.47
     maravillosas
    1.47
     individuals
    1.46
    すすめ
    1.45
     хто
    1.45
    )]{
    1.42
    Activations Density 0.139%

    No Known Activations