© 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. 36053
    Prev
    Next
    INDEX
    Explanations

    logarithms and number bases

    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
     during
    -1.03
     еще
    -0.94
     '../
    -0.92
    ۹
    -0.92
     Griswold
    -0.89
    Ｆ
    -0.89
     ещё
    -0.88
    上一
    -0.87
    RTLE
    -0.87
     abenço
    -0.87
    POSITIVE LOGITS
     herself
    1.14
     spanish
    0.97
    çais
    0.96
    eapples
    0.96
     ближай
    0.95
     Schwierigkeiten
    0.95
     commonest
    0.93
     σήμερα
    0.93
     čia
    0.93
    さすがに
    0.93
    Activations Density 0.012%

    No Known Activations