© 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. 22-GEMMASCOPE-RES-131K
    7. 64327
    Prev
    Next
    INDEX
    Explanations

    This leads to

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

    The neuron detects discourse-transition demonstrative pronouns (e.g. “This,” “That”) used to introduce or link sentences.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    datable
    -1.10
     también
    -1.05
     or
    -1.05
    しては
    -1.02
     myös
    -1.02
    当时的
    -0.98
    también
    -0.96
    Также
    -0.95
    volves
    -0.95
     também
    -0.94
    POSITIVE LOGITS
     allow
    1.33
     allows
    1.31
     makes
    1.30
    Along
    1.17
     khiến
    1.14
    Another
    1.13
    Having
    1.13
     coupled
    1.13
     provide
    1.09
    ทำให้
    1.09
    Activations Density 0.034%

    No Known Activations