© 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. 29923
    Prev
    Next
    INDEX
    Explanations

    track listing

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

    The neuron responds to numeric document markers—tokens containing digits such as years, track numbers, and other numbered list items.

    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
     końca
    -0.86
    iology
    -0.76
     dür
    -0.75
    čiu
    -0.74
     hydrothermal
    -0.71
     Joomla
    -0.69
     Alexand
    -0.69
    numRows
    -0.68
    து
    -0.68
     корпус
    -0.68
    POSITIVE LOGITS
     track
    3.42
     Track
    2.92
    track
    2.91
    Track
    2.72
    Tracklist
    2.59
    TRACK
    2.48
     TRACK
    2.31
     tracks
    1.84
     tracking
    1.80
     tracked
    1.72
    Activations Density 0.056%

    No Known Activations