© 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. 3421
    Prev
    Next
    INDEX
    Explanations

    that + descriptive word

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

    This neuron fires strongly on demonstrative and general reference words—especially “that,” “those,” and similar pronouns used to point back or refer generally.

    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
     shenanigans
    -1.17
     competencies
    -1.10
    Mvh
    -1.03
     antics
    -1.02
    为什么会
    -1.00
    Друзья
    -0.99
    enciales
    -0.99
     советы
    -0.98
    があると
    -0.97
    مقال
    -0.96
    POSITIVE LOGITS
     little
    1.54
     big
    1.53
     dreaded
    1.38
     nice
    1.37
     giant
    1.30
     elusive
    1.30
     old
    1.29
     extra
    1.26
     beautiful
    1.25
     long
    1.23
    Activations Density 0.049%

    No Known Activations