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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73923
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical operations

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

    The neuron strongly activates on numeric tokens—that is, individual digits or numbers in the text.

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

    No Comments

    Negative Logits
    後期
    -1.36
     procedente
    -1.34
    后续
    -1.29
     interesados
    -1.28
     there
    -1.28
     things
    -1.27
     functions
    -1.26
     in
    -1.23
     realms
    -1.23
    統領
    -1.22
    POSITIVE LOGITS
    妡
    1.35
    趿
    1.33
    dijo
    1.30
     fotografie
    1.30
     specchio
    1.27
     laiss
    1.24
    ALREADY
    1.22
    Shown
    1.21
     largely
    1.21
    quête
    1.20
    Activations Density 0.021%

    No Known Activations