© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 32641
    Prev
    Next
    INDEX
    Explanations

    comes to

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

    This neuron detects the discourse phrase “when it comes to” (and its variant “comes to”) introducing a topic.

    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
     všechny
    -1.44
    vertissement
    -1.30
     casero
    -1.27
     DÍA
    -1.25
     BERKELEY
    -1.23
    ズニー
    -1.22
     fuis
    -1.21
    鯔
    -1.20
    ásticos
    -1.20
     liso
    -1.20
    POSITIVE LOGITS
     to
    2.64
    of
    1.57
    a
    1.37
     <
    1.27
     of
    1.27
     about
    1.20
     zelfs
    1.16
    but
    1.14
     alors
    1.13
     hinsichtlich
    1.13
    Activations Density 0.016%

    No Known Activations