© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75106
    Prev
    Next
    INDEX
    Explanations

    quantities and digits

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

    This neuron detects references to specific place‐value digits (e.g. “tens digit,” “hundreds digit,” “thousand‐s digit”) in math questions.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     atractivos
    -1.27
    ּוֹ
    -1.23
    וּ
    -1.19
    ִּ
    -1.16
    ımı
    -1.16
    Ὁ
    -1.14
     бампер
    -1.13
     BRAZIL
    -1.13
    这本书
    -1.10
     accueil
    -1.09
    POSITIVE LOGITS
     ویتامین
    1.30
     Saturday
    1.21
     сборной
    1.15
     katholischen
    1.13
    一抹
    1.13
     religieuses
    1.13
    食欲
    1.13
    寂
    1.11
    ということは
    1.10
     Pfar
    1.10
    Activations Density 0.001%

    No Known Activations