© 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. 10-GEMMASCOPE-RES-131K
    7. 111106
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ation' or 'ing'

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

    This neuron responds to long or unusual subword tokens—i.e. rare, morphologically complex pieces of 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_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
     
    -1.54
    .
    -1.45
     douze
    -1.27
     prohibiting
    -1.25
     veinte
    -1.21
     véritables
    -1.20
    cterms
    -1.20
     paysages
    -1.19
    がとても
    -1.13
     visualizing
    -1.13
    POSITIVE LOGITS
     отличается
    1.81
     them
    1.69
     assumes
    1.58
     обеспечивает
    1.55
     продолжает
    1.52
     adapts
    1.52
     seems
    1.50
     adds
    1.49
    iální
    1.48
    为什么会
    1.48
    Activations Density 25.774%

    No Known Activations