© 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. 41697
    Prev
    Next
    INDEX
    Explanations

    baseball teams

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

    The neuron strongly activates on proper names of Major League Baseball teams and ballparks (e.g. team names, stadium names, divisions).

    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
    4
    -1.49
    3
    -1.29
     Creativity
    -1.21
    |
    -1.20
     Navidad
    -1.16
     sudadera
    -1.16
    <strong>
    -1.13
    最後
    -1.11
     chicas
    -1.10
     ellas
    -1.09
    POSITIVE LOGITS
    杙
    1.28
    𝟳
    1.23
     responsabilità
    1.23
    MfG
    1.21
     cruzar
    1.20
     būt
    1.18
     protegida
    1.18
     where
    1.18
     desafi
    1.17
    马逊
    1.17
    Activations Density 0.084%

    No Known Activations