© 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. 10-GEMMASCOPE-RES-131K
    7. 68489
    Prev
    Next
    INDEX
    Explanations

    quantity of seconds

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

    The neuron fires on occurrences of the word “seconds,” i.e. mentions of time intervals measured in seconds.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ꦢ
    -2.64
     trouvez
    -2.59
     appelez
    -2.45
    ormány
    -2.39
    盌
    -2.36
    鱲
    -2.31
    卨
    -2.25
    .”
    -2.23
    
    -2.23
     哪些
    -2.22
    POSITIVE LOGITS
    that
    3.09
    $
    2.86
    "
    2.80
    ↵
    2.78
     "",
    2.58
    le
    2.52
    .
    2.38
    it
    2.23
    the
    2.20
     "";
    2.17
    Activations Density 0.004%

    No Known Activations