© 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. 45635
    Prev
    Next
    INDEX
    Explanations

    actions and their targets

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

    This neuron detects phrasal verbs—combinations of a base verb and a following particle (preposition or adverb) such as “slapped on,” “shaved off,” “hammer out,” or “claw back.”

    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
     alebo
    -1.64
     или
    -1.61
    或
    -1.59
     أو
    -1.56
    datable
    -1.54
     یا
    -1.52
    та
    -1.51
    琑
    -1.50
     veya
    -1.50
    や
    -1.47
    POSITIVE LOGITS
    Another
    1.60
    おまけ
    1.55
    必要があります
    1.48
    ixel
    1.38
     but
    1.38
    Between
    1.36
    ,
    1.34
    -
    1.34
    Mä
    1.32
     пребы
    1.31
    Activations Density 0.244%

    No Known Activations