© 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. 10-GEMMASCOPE-RES-131K
    7. 99536
    Prev
    Next
    INDEX
    Explanations

    significant effect or correlation

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

    The neuron activates on numeric values and statistical measurements (e.g. significance levels, effect sizes, counts, and other 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
    崤
    -1.82
    ৢ
    -1.70
     teraz
    -1.67
     transfé
    -1.58
     Ө
    -1.56
    ୩
    -1.52
     )}
    -1.51
     esas
    -1.49
    剮
    -1.48
     imágenes
    -1.47
    POSITIVE LOGITS
    などなど
    1.59
     ませ
    1.57
    越来越多
    1.53
     \
    1.48
     Generales
    1.45
     經典
    1.41
     兩
    1.41
    }{
    1.40
    （※
    1.34
    一緒
    1.32
    Activations Density 0.025%

    No Known Activations