© 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. 24947
    Prev
    Next
    INDEX
    Explanations

    mathematical function definitions

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

    The neuron is primarily detecting numerical tokens (digits or numbers) in mathematical expressions.

    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
    rumah
    -0.98
     其他
    -0.94
    ھ
    -0.93
     swojej
    -0.91
    ͦ
    -0.89
    bucks
    -0.89
     bedenken
    -0.88
    ㅉ
    -0.88
    ˣ
    -0.86
    ganggu
    -0.86
    POSITIVE LOGITS
     caminh
    1.04
     amitié
    0.93
    assertNotNull
    0.93
    ICIAL
    0.90
    1
    0.90
    ianum
    0.88
     nasceu
    0.88
     chỗ
    0.87
     deletions
    0.87
     veio
    0.87
    Activations Density 0.050%

    No Known Activations