© 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. 20961
    Prev
    Next
    INDEX
    Explanations

    a or an followed by a word

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

    The neuron primarily fires on the indefinite article “a” (and its variant “an”).

    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
     is
    -2.06
     most
    -1.47
     it
    -1.38
    tivité
    -1.35
    Ἢ
    -1.33
    listItem
    -1.31
     😂
    -1.29
    を紹介
    -1.28
     previous
    -1.27
     fortal
    -1.27
    POSITIVE LOGITS
    ка
    1.55
     efficaces
    1.49
    我们
    1.45
     toujours
    1.45
    ড়
    1.41
     nhưng
    1.30
    Миха
    1.29
     ДО
    1.29
    世界
    1.27
     évé
    1.25
    Activations Density 0.025%

    No Known Activations