© 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. 15774
    Prev
    Next
    INDEX
    Explanations

    sports positions

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

    The main thing this neuron does is find mentions of athletic playing positions (e.g. baseball, football, or other sports roles).

    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
    ↵↵↵
    -1.55
    ↵↵↵↵
    -1.27
    酝
    -1.23
     présidentielle
    -1.23
    ↵↵↵↵↵
    -1.22
    ↵↵↵↵↵↵↵↵
    -1.20
    ↵↵↵↵↵↵
    -1.19
    它的
    -1.19
    řízení
    -1.18
     (~(
    -1.18
    POSITIVE LOGITS
     then
    1.82
     for
    1.81
    if
    1.51
     we
    1.34
     conteúdos
    1.27
     komunikasi
    1.27
     municípios
    1.26
     inoltre
    1.20
     ilusión
    1.19
     affrontare
    1.19
    Activations Density 0.041%

    No Known Activations