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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40758
    Prev
    Next
    INDEX
    Explanations

    cities in sports contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    他
    -1.32
    šej
    -1.31
     completamente
    -1.25
     wechseln
    -1.23
     obrázok
    -1.23
    vajú
    -1.23
     verschillende
    -1.22
     však
    -1.22
    different
    -1.21
    actually
    -1.20
    POSITIVE LOGITS
     this
    1.77
     शुर
    1.45
     polícia
    1.41
     prefeitura
    1.34
    ﱠ
    1.34
     हमारा
    1.27
     hende
    1.26
    reportWebVitals
    1.26
     cidade
    1.22
     enligt
    1.22
    Activations Density 0.077%

    No Known Activations