© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111414
    Prev
    Next
    INDEX
    Explanations

    relative clauses defining nouns

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

    The neuron identifies words (and short phrases) that introduce or signal relative/subordinate clauses—e.g. where, that, which, is, are.

    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
     alrededores
    -1.65
     there
    -1.55
     acoged
    -1.55
     instead
    -1.39
     atractiva
    -1.38
    amente
    -1.31
     puentes
    -1.29
     ervoor
    -1.27
     onderdeel
    -1.26
    ische
    -1.25
    POSITIVE LOGITS
    What
    1.55
     However
    1.51
    ほとんど
    1.40
    我們
    1.38
     щодо
    1.30
    ssaint
    1.30
    ekw
    1.29
     號
    1.28
     Subsequently
    1.28
    什麼
    1.27
    Activations Density 0.152%

    No Known Activations