© 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. 8833
    Prev
    Next
    INDEX
    Explanations

    code and math syntax

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

    The neuron fires on numeric literals (especially numbers with digits and decimal points) wherever they appear 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
     but
    -1.81
     a
    -1.77
     so
    -1.74
    援助
    -1.22
     to
    -1.19
    んでいた
    -1.16
     @
    -1.16
    一定的
    -1.14
     nhưng
    -1.14
     dergleichen
    -1.13
    POSITIVE LOGITS
    预计
    1.28
    ynchronously
    1.27
     vectoriales
    1.23
     positivas
    1.18
     kesan
    1.16
     completas
    1.16
    細節
    1.16
     wezen
    1.15
     bancaria
    1.14
     magnética
    1.14
    Activations Density 0.028%

    No Known Activations