© 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. 10-GEMMASCOPE-RES-131K
    4. 22600
    Prev
    Next
    INDEX
    Explanations

    past participial descriptions

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

    The neuron activates on numeric expressions (particularly integers and decimal numbers).

    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
     fourni
    -1.73
     véhic
    -1.62
     choses
    -1.59
     bénéficier
    -1.57
    
    -1.50
     recargable
    -1.43
     icône
    -1.42
     ceea
    -1.42
    BOURNE
    -1.42
     déclar
    -1.41
    POSITIVE LOGITS
     in
    2.58
     with
    2.22
     from
    2.09
     that
    2.03
     to
    1.95
     for
    1.93
     by
    1.92
     on
    1.67
     and
    1.65
     at
    1.65
    Activations Density 0.084%

    No Known Activations