© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 6810
    Prev
    Next
    INDEX
    Explanations

    football midfielder position

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

    The main thing this neuron does is detect mentions of “midfielder” or other midfield‐related positions in football.

    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
    🫃
    -1.28
     irré
    -1.26
     اذا
    -1.24
     métodos
    -1.22
     explicado
    -1.21
     ещё
    -1.21
     rigue
    -1.21
    titanic
    -1.21
     vêtements
    -1.20
    however
    -1.20
    POSITIVE LOGITS
     then
    1.49
     or
    1.27
     into
    1.20
     for
    1.16
    <tr>
    1.16
    bigliamento
    1.14
     so
    1.13
    acterium
    1.12
    というわけで
    1.10
    }\
    1.09
    Activations Density 0.048%

    No Known Activations