© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45484
    Prev
    Next
    INDEX
    Explanations

    verbs showing causation or influence

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

    The neuron fires on strong action verbs that denote causing, promoting, activating, or otherwise influencing processes.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     veren
    -1.32
    などが
    -1.31
    方が
    -1.19
     it
    -1.19
     emballage
    -1.17
    Jojo
    -1.17
     murs
    -1.16
    뵙
    -1.16
     unending
    -1.16
    dags
    -1.13
    POSITIVE LOGITS
    If
    1.77
    uchungen
    1.32
    when
    1.32
    Before
    1.31
    While
    1.29
    With
    1.25
     if
    1.23
     this
    1.18
     various
    1.18
    if
    1.14
    Activations Density 0.445%

    No Known Activations