© 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. 98405
    Prev
    Next
    INDEX
    Explanations

    Tibet, Bhutan, Dalai Lama

    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
     such
    -1.63
    壜
    -1.35
     kanak
    -1.32
     adresa
    -1.31
     kirim
    -1.27
     internasional
    -1.27
     kuu
    -1.24
     wani
    -1.23
     では
    -1.23
     adesi
    -1.21
    POSITIVE LOGITS
     Bhutan
    1.68
     Tibetan
    1.27
    AfterViewInit
    1.13
    гряз
    1.13
     altitude
    1.08
    uticos
    1.07
    ıyordu
    1.07
    êques
    1.07
     Buddhist
    1.07
     вони
    1.07
    Activations Density 0.009%

    No Known Activations