© 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. 127673
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on standalone numeric tokens (pure sequences of digits) wherever they appear.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    numbers and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     vorsichtig
    -0.91
    נוּ
    -0.88
    多彩
    -0.85
    Brainz
    -0.84
    ghijklmnop
    -0.84
     beb
    -0.84
     komplette
    -0.84
    LEGGI
    -0.82
    鉍
    -0.82
     sonor
    -0.81
    POSITIVE LOGITS
    ともに
    0.96
    共に
    0.96
     keduanya
    0.91
    どっち
    0.91
     entrambi
    0.89
    这两个
    0.87
     nová
    0.85
     both
    0.84
    这两
    0.84
     båda
    0.82
    Activations Density 0.061%

    No Known Activations