© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93212
    Prev
    Next
    INDEX
    Explanations

    preposition + the

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

    The neuron strongly fires on common function words—especially articles and prepositions like “the,” “for,” and “of.”

    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
     a
    -1.24
     its
    -1.10
     their
    -0.94
    
    -0.93
     those
    -0.93
     during
    -0.93
    During
    -0.93
    風が
    -0.89
     same
    -0.87
    ingtones
    -0.87
    POSITIVE LOGITS
     the
    3.55
     året
    1.01
     giornata
    0.98
    新年
    0.92
    目の
    0.90
     дня
    0.88
     день
    0.88
    ²-
    0.86
     résultat
    0.84
    csolódó
    0.83
    Activations Density 0.047%

    No Known Activations