© 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. 68929
    Prev
    Next
    INDEX
    Explanations

    Special Education, Consumer sentiments, Wolfgang Webner

    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
    ্যান
    -1.05
     diversidad
    -0.96
     acción
    -0.96
    נגלית
    -0.94
     artículo
    -0.94
     enseñanza
    -0.93
     cantora
    -0.93
     investigación
    -0.93
     Bearbeitung
    -0.91
     compounds
    -0.91
    POSITIVE LOGITS
     you
    1.13
     we
    1.08
     Terkait
    1.05
     Pokud
    1.04
     biała
    1.03
     Dzięki
    0.99
    if
    0.98
     nonatomic
    0.97
     Jeśli
    0.97
     Dlatego
    0.94
    Activations Density 0.000%

    No Known Activations