© 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. 15643
    Prev
    Next
    INDEX
    Explanations

    in phrases like 'in the'

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

    The neuron strongly activates on numeric tokens—especially multi‐digit numbers and decimal values—i.e. it detects 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
     jednej
    -1.74
    也會
    -1.66
     Eigentü
    -1.51
     ВЫ
    -1.41
    ¹,
    -1.35
    妯
    -1.34
     Pokud
    -1.33
    無論
    -1.31
     иностран
    -1.30
    ického
    -1.29
    POSITIVE LOGITS
     which
    2.53
     and
    2.48
     how
    1.97
     what
    1.72
     where
    1.70
    >
    1.64
    ୈ
    1.60
     his
    1.57
     with
    1.54
    1.48
    Activations Density 0.339%

    No Known Activations