© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47087
    Prev
    Next
    INDEX
    Explanations

    previously or before

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

    The neuron detects phrases expressing prior experience, especially the word “before” in contexts like “done this kind of thing before” or “seen it before.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     while
    -0.99
     späteren
    -0.99
     when
    -0.98
     later
    -0.97
     pēc
    -0.91
     after
    -0.90
    现在的
    -0.88
    elif
    -0.87
     luego
    -0.86
     Subsequent
    -0.84
    POSITIVE LOGITS
     previously
    3.95
     before
    3.66
     sebelumnya
    3.53
    previously
    3.38
    Previously
    3.25
     Previously
    2.84
     auparavant
    2.69
     previous
    2.61
     zuvor
    2.56
    before
    2.50
    Activations Density 0.086%

    No Known Activations