© 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. 34-GEMMASCOPE-RES-131K
    7. 56702
    Prev
    Next
    INDEX
    Explanations

    legal, technical, and descriptive terms

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

    The neuron responds to numeric tokens—digits or number literals wherever they appear.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    tutup
    -0.76
    ฉ
    -0.70
    rable
    -0.67
     rod
    -0.66
    Handling
    -0.65
     plass
    -0.65
     عامة
    -0.65
    فس
    -0.63
     Vanguard
    -0.63
     rods
    -0.63
    POSITIVE LOGITS
    dare
    0.71
     thùng
    0.69
     الشرق
    0.69
    やった
    0.67
    kia
    0.66
     кри
    0.66
    inventory
    0.66
    assé
    0.65
     promi
    0.65
     リスト
    0.64
    Activations Density 0.057%

    No Known Activations