© 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. 22824
    Prev
    Next
    INDEX
    Explanations

    such as, called, named

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

    This neuron activates on numeric tokens—especially decimal values—i.e. it detects measurements or numbers in the text.

    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
     with
    -3.42
     that
    -2.22
     on
    -2.16
     as
    -2.14
     and
    -2.09
     which
    -2.00
     you
    -1.80
     from
    -1.79
     for
    -1.71
     because
    -1.71
    POSITIVE LOGITS
     tratamientos
    1.66
     secado
    1.66
     enfri
    1.54
     burada
    1.54
     ajouter
    1.51
     empêcher
    1.51
     colgar
    1.50
     remplacer
    1.50
     gier
    1.45
     moviliz
    1.44
    Activations Density 0.288%

    No Known Activations