© 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. 76291
    Prev
    Next
    INDEX
    Explanations

    morphological and grammatical structure

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

    The neuron strongly activates on technical linguistic feature terms (e.g. “morphological type,” “word classes,” “constituent order,” “grammatical relations,” 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
    ዕ
    -0.82
     vzd
    -0.76
     concurrency
    -0.74
    bulaire
    -0.72
    Concert
    -0.72
     preposition
    -0.71
    スムーズ
    -0.71
     kalimat
    -0.71
    ровании
    -0.71
     Sentence
    -0.70
    POSITIVE LOGITS
     morphological
    1.49
     morphology
    1.38
     morpho
    1.24
     Morphology
    1.21
     Morpho
    1.13
     productivity
    1.07
    Morphology
    1.06
     affix
    1.05
     deriv
    1.02
    mor
    1.01
    Activations Density 0.034%

    No Known Activations