© 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. 71621
    Prev
    Next
    INDEX
    Explanations

    the start of specific noun phrases

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

    The neuron primarily activates on occurrences of the definite article “the.”

    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
    ↵
    -1.07
    </em>
    -0.99
    )
    -0.97
    ,
    -0.94
    ないです
    -0.92
     bezüglich
    -0.92
     múltiples
    -0.91
     Presumably
    -0.91
    </b>
    -0.91
     эмо
    -0.91
    POSITIVE LOGITS
     மற்றும்
    1.28
    cendo
    1.24
     krä
    1.15
     conseille
    1.12
     автомобиль
    1.12
    ILDREN
    1.11
    менты
    1.09
     אנשים
    1.09
    hanced
    1.09
    ジェクト
    1.09
    Activations Density 0.039%

    No Known Activations