© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105334
    Prev
    Next
    INDEX
    Explanations

    group stage round robin

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

    The neuron flags mentions of sports‐tournament structure labels—especially “Group” stages, championship rounds, and similar event grouping terms.

    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
     când
    -1.45
    毉
    -1.38
     다른
    -1.37
     viață
    -1.36
     extraer
    -1.35
    новые
    -1.34
    ujące
    -1.31
     murale
    -1.30
     дів
    -1.30
     It
    -1.27
    POSITIVE LOGITS
     of
    2.16
     \
    1.55
    at
    1.38
     ''
    1.38
    <bos>
    1.35
     et
    1.30
     for
    1.28
    Rejo
    1.25
     \"
    1.24
     all
    1.22
    Activations Density 0.020%

    No Known Activations