© 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. 22-GEMMASCOPE-RES-131K
    7. 34046
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    This neuron selectively detects numerical measurement values—especially decimal or high-magnitude numbers—in scientific contexts.

    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
    Magdalena
    -0.96
    staben
    -0.89
     Trotsky
    -0.88
    elni
    -0.88
     næste
    -0.85
    Buen
    -0.85
     alugar
    -0.85
    儕
    -0.85
    Mie
    -0.85
     bantu
    -0.85
    POSITIVE LOGITS
     kombiniert
    1.00
     різних
    0.98
     dalej
    0.97
    ៖
    0.93
     обороны
    0.93
     Capítulo
    0.93
    เริ่ม
    0.92
     wciąż
    0.91
     пациентов
    0.90
     size
    0.90
    Activations Density 0.012%

    No Known Activations