© 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. 34-GEMMASCOPE-RES-131K
    7. 6962
    Prev
    Next
    INDEX
    Explanations

    determiner before specific nouns

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

    The neuron acts as a detector for the definite article “the” (i.e. very common function words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    kasten
    -1.15
    tività
    -1.13
    ‌.
    -1.13
     BEHIND
    -1.11
     ára
    -1.06
     créateur
    -1.06
    anywhere
    -1.05
     acteur
    -1.05
    krieg
    -1.04
    ofing
    -1.02
    POSITIVE LOGITS
     other
    1.94
     only
    1.77
     same
    1.60
     slightly
    1.54
     now
    1.52
     already
    1.46
     very
    1.45
     little
    1.42
     small
    1.41
     also
    1.40
    Activations Density 0.032%

    No Known Activations