© 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. 38666
    Prev
    Next
    INDEX
    Explanations

    time to or ready to

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

    The neuron activates strongly on numeric expressions (digits, quantities, measurements, and time values).

    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
    4
    -1.53
    6
    -1.48
    3
    -1.34
    0
    -1.28
     and
    -1.27
     if
    -1.26
    7
    -1.25
    .......
    -1.24
    '
    -1.23
    -----------
    -1.23
    POSITIVE LOGITS
    睃
    1.53
    СКИ
    1.50
    secutions
    1.45
     to
    1.44
     diſ
    1.43
     was
    1.42
    ሖ
    1.39
    ଃ
    1.33
    новения
    1.33
    (
    1.30
    Activations Density 0.014%

    No Known Activations