© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 280
    Prev
    Next
    INDEX
    Explanations

    sports leagues and levels

    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_22/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
    懶
    -1.13
    誣
    -1.09
     escuelas
    -0.98
     család
    -0.97
    慫
    -0.95
    ないです
    -0.94
    ことはありません
    -0.93
     cavo
    -0.92
     allarg
    -0.90
     sko
    -0.89
    POSITIVE LOGITS
     лест
    1.09
    AttributedString
    1.05
     where
    1.05
    ани
    1.03
    垣
    0.99
    erialization
    0.99
     staircase
    0.99
    Await
    0.98
    ziali
    0.97
    цене
    0.96
    Activations Density 0.059%

    No Known Activations