© 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. 22734
    Prev
    Next
    INDEX
    Explanations

    before they are

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

    This neuron activates on the auxiliary “are,” whether spelled out or contracted as ’re.

    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
    ).
    -1.88
     didn
    -1.70
    ・「
    -1.60
     DÍA
    -1.45
     otrzy
    -1.45
    屨
    -1.44
     být
    -1.42
    olutions
    -1.42
    Примеча
    -1.41
     couldn
    -1.40
    POSITIVE LOGITS
     که
    1.93
    prender
    1.72
     установка
    1.64
    ”
    1.63
    şak
    1.58
    ,”
    1.52
    cfr
    1.52
    幛
    1.51
    曖昧さ回避
    1.51
     والتي
    1.48
    Activations Density 0.017%

    No Known Activations