© 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. 19109
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by verbs

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

    The neuron activates on auxiliary and modal verbs (e.g. is, will, should, could, would) rather than on main content 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
     reele
    -1.38
     formes
    -1.33
    nek
    -1.31
    ଃ
    -1.30
     ás
    -1.30
    τους
    -1.29
    atiques
    -1.29
     Cualquier
    -1.28
    偶尔
    -1.28
     appris
    -1.27
    POSITIVE LOGITS
     in
    2.17
     when
    1.82
     at
    1.81
     with
    1.80
     which
    1.77
     went
    1.63
     about
    1.55
     they
    1.54
     difference
    1.52
     it
    1.48
    Activations Density 0.045%

    No Known Activations