© 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. 22-GEMMASCOPE-RES-131K
    7. 66180
    Prev
    Next
    INDEX
    Explanations

    verbs in multiple languages

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

    The neuron activates on conjugated (finite) verb forms (e.g. present‐ and perfect‐tense verbs) across different languages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    it
    -2.03
    It
    -2.00
     has
    -1.98
     In
    -1.94
     increase
    -1.90
     is
    -1.88
     "
    -1.86
     can
    -1.83
     it
    -1.81
     '
    -1.78
    POSITIVE LOGITS
     trám
    2.22
     ſeveral
    2.20
    são
    2.08
     alemania
    2.06
    ⑊
    1.98
     juſt
    1.96
    recette
    1.95
     夜景
    1.92
    ཫ
    1.91
    ícone
    1.88
    Activations Density 0.043%

    No Known Activations