© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 120092
    Prev
    Next
    INDEX
    Explanations

    determiner followed by specific noun

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

    The neuron detects definite and proximal determiners (e.g. "the," "this," "these") that introduce noun phrases.

    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
    ཽ
    -1.55
    葑
    -1.50
    čno
    -1.48
    咵
    -1.44
    
    -1.43
     ofreci
    -1.41
    菫
    -1.41
    嘡
    -1.40
     modalidades
    -1.37
    edere
    -1.35
    POSITIVE LOGITS
     was
    2.25
     already
    1.89
    "
    1.74
    '
    1.68
     are
    1.67
     again
    1.62
    ’
    1.54
    ‘
    1.54
     finally
    1.53
    jooq
    1.48
    Activations Density 0.056%

    No Known Activations