© 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. 3474
    Prev
    Next
    INDEX
    Explanations

    size, duration, and time units

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

    The neuron flags tokens that contain or represent numeric values (digits), including numbers themselves and identifiers suffixed with digits.

    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
    timers
    -0.84
    ouw
    -0.83
     at
    -0.82
     MOQ
    -0.76
     of
    -0.75
    ่าน
    -0.75
    方を
    -0.74
     www
    -0.73
     people
    -0.73
     up
    -0.73
    POSITIVE LOGITS
     seconds
    1.40
     milliseconds
    1.25
     meters
    1.12
     milli
    1.11
     millimeters
    1.09
    毫
    1.08
    Seconds
    1.08
     bytes
    1.06
     in
    1.03
     metres
    1.02
    Activations Density 0.039%

    No Known Activations