© 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. 34-GEMMASCOPE-RES-131K
    7. 62449
    Prev
    Next
    INDEX
    Explanations

    state changes followed by prepositions

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

    The neuron detects verbs in their past-tense or past-participle form ending in “-ed.”

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     necessarily
    -1.63
     обязательно
    -1.48
     primarily
    -1.48
     specifically
    -1.46
     squarely
    -1.36
     соответственно
    -1.34
    主要是
    -1.31
     easily
    -1.31
     ultimately
    -1.27
    大致
    -1.23
    POSITIVE LOGITS
     แท
    0.98
    ighed
    0.97
    huge
    0.95
    会在
    0.95
     guarn
    0.94
     agences
    0.93
     negoci
    0.92
     bolas
    0.91
    Jawaban
    0.90
    carus
    0.90
    Activations Density 0.299%

    No Known Activations