© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31760
    Prev
    Next
    INDEX
    Explanations

    quantities and numbers

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

    The neuron fires on numeric measurement tokens (e.g. dosage amounts, counts, and other standalone numbers).

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

    No Comments

    Negative Logits
     χρόνια
    -1.05
     niektó
    -0.99
     wiele
    -0.98
    |}{}
    -0.96
    ンピ
    -0.95
     años
    -0.94
    遑
    -0.93
    middels
    -0.91
     years
    -0.89
     []:
    -0.89
    POSITIVE LOGITS
     one
    3.22
     two
    2.67
     ONE
    2.06
     ½
    2.03
     five
    2.00
     một
    1.98
     three
    1.98
    one
    1.98
    two
    1.90
     ¼
    1.88
    Activations Density 0.147%

    No Known Activations