© 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. 98645
    Prev
    Next
    INDEX
    Explanations

    practically

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

    The neuron strongly activates on the adverb “practically.”

    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
     of
    -3.13
     The
    -2.50
     Problemen
    -2.06
     configurações
    -2.06
    replyreport
    -2.06
      
    -2.05
    б
    -2.03
    нку
    -2.02
     semua
    -2.00
     ?
    -1.98
    POSITIVE LOGITS
    ੴ
    2.23
    酲
    2.20
     instig
    2.17
     條
    2.11
    تیجه
    2.02
    er
    2.02
     fossero
    1.99
    骈
    1.95
    (^^)
    1.94
     場所
    1.94
    Activations Density 0.005%

    No Known Activations