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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39314
    Prev
    Next
    INDEX
    Explanations

    taking into account subsequent factors

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

    The neuron detects numeric data—especially decimal or floating‐point 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
    j
    -1.93
    x
    -1.79
    щей
    -1.63
    rant
    -1.62
    um
    -1.54
    時
    -1.54
    之上
    -1.52
    有
    -1.51
    da
    -1.50
    ivotopis
    -1.46
    POSITIVE LOGITS
    聍
    2.38
     wholeheartedly
    1.93
    ⟝
    1.70
    迨
    1.69
     waż
    1.69
     proactively
    1.68
     ouvido
    1.66
     vividly
    1.66
     consider
    1.64
     whom
    1.63
    Activations Density 0.042%

    No Known Activations