© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27858
    Prev
    Next
    INDEX
    Explanations

    cities, countries, and regions

    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
    çim
    -1.10
     murano
    -1.04
    řit
    -1.03
     myster
    -0.98
     barnet
    -0.97
    ときは
    -0.94
     then
    -0.94
    ようです
    -0.93
    ленность
    -0.92
     {$\
    -0.91
    POSITIVE LOGITS
    резать
    1.11
     mesto
    1.09
     doby
    1.09
    tonsoft
    1.09
    Dış
    1.05
     sklep
    1.05
    ጺ
    1.05
     histó
    1.05
     by
    1.04
     during
    1.02
    Activations Density 0.108%

    No Known Activations