© 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. 64997
    Prev
    Next
    INDEX
    Explanations

    returning or when

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

    This neuron specializes in spotting words that occur immediately adjacent to numeric values or measurements.

    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
     how
    -1.62
    上面
    -1.55
     something
    -1.54
     same
    -1.44
     lots
    -1.41
    mė
    -1.38
     związ
    -1.37
     ebenso
    -1.34
    所以
    -1.32
     écoulé
    -1.29
    POSITIVE LOGITS
     of
    3.14
     in
    2.39
    帰る
    1.73
    際には
    1.66
     salg
    1.48
     than
    1.42
     cantik
    1.41
    がっ
    1.39
     deri
    1.31
    帰って
    1.31
    Activations Density 0.068%

    No Known Activations