© 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. 59202
    Prev
    Next
    INDEX
    Explanations

    places after prepositions

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

    The neuron strongly responds to common function words—especially high‐frequency prepositions and articles like “of,” “the,” “in,” “on,” “and,” etc.

    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
    是一款
    -1.01
     geene
    -0.99
     hígado
    -0.95
    Задание
    -0.94
     IMPLICATIONS
    -0.90
    𐍆
    -0.90
     bénéfices
    -0.89
     CALIFORN
    -0.89
     réel
    -0.88
    thâu
    -0.87
    POSITIVE LOGITS
     Bear
    1.16
     Hidden
    1.16
     Little
    1.14
     where
    1.10
     Lower
    1.07
     Devil
    1.07
     Eight
    1.05
     Five
    1.05
     Turkey
    1.02
     around
    1.01
    Activations Density 0.067%

    No Known Activations