© 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. 34-GEMMASCOPE-RES-131K
    4. 110682
    Prev
    Next
    INDEX
    Explanations

    city names in sports

    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_34/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
    長男
    -0.93
     contributors
    -0.84
     儿
    -0.84
    jména
    -0.84
     rég
    -0.82
    子が
    -0.80
     óptica
    -0.80
     丝
    -0.79
     deje
    -0.78
     issues
    -0.77
    POSITIVE LOGITS
     Philadelphia
    2.27
     Chicago
    2.23
     Detroit
    2.14
     Atlanta
    2.11
     Dallas
    2.11
     Houston
    2.03
     Boston
    2.00
     Cleveland
    1.98
     Seattle
    1.82
     Denver
    1.82
    Activations Density 0.092%

    No Known Activations