© 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. 37885
    Prev
    Next
    INDEX
    Explanations

    change of noun

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

    This neuron activates on occurrences of the phrase “change 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
     ян
    -0.97
     („
    -0.94
    ynie
    -0.93
    を
    -0.91
    WEBP
    -0.90
    xiv
    -0.89
    ilon
    -0.89
    Thing
    -0.88
     мин
    -0.88
    way
    -0.88
    POSITIVE LOGITS
     sorts
    1.16
     both
    1.10
     opinion
    1.07
     which
    1.04
     having
    1.00
     purpose
    0.99
     resources
    0.96
     not
    0.94
     pace
    0.94
     circumstance
    0.94
    Activations Density 0.035%

    No Known Activations