© 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. 13252
    Prev
    Next
    INDEX
    Explanations

    be verb and participle

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

    The neuron detects auxiliary and linking verbs (especially forms of “to be” and related auxiliaries) that signal states or passive constructions.

    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
    zension
    -1.60
    Среди
    -1.50
    Ṭ
    -1.45
    Есть
    -1.43
    ፅ
    -1.39
     誰
    -1.38
    )),
    -1.38
    dibility
    -1.38
     there
    -1.36
    when
    -1.36
    POSITIVE LOGITS
    ↵↵
    1.68
     samarbeid
    1.57
     between
    1.53
     kampen
    1.39
    之前的
    1.39
     “
    1.37
     kroppen
    1.30
     The
    1.30
     שה
    1.25
     vår
    1.25
    Activations Density 0.162%

    No Known Activations