© 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. 70173
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions

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

    The neuron activates on relational linking verbs or verb phrases that describe how one concept is related to, depends on, consists of, or is associated with another.

    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
     conviene
    -1.03
     Things
    -1.00
    Kritik
    -0.96
    jando
    -0.96
     felpa
    -0.96
     cualidades
    -0.95
     conexiones
    -0.95
     trampa
    -0.93
     nạ
    -0.92
     început
    -0.91
    POSITIVE LOGITS
     to
    2.58
     of
    1.82
     into
    1.64
     on
    1.59
     also
    1.33
     for
    1.09
     onto
    0.98
    Życiorys
    0.94
     например
    0.89
    了
    0.88
    Activations Density 0.189%

    No Known Activations