© 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. 10-GEMMASCOPE-RES-131K
    7. 110962
    Prev
    Next
    INDEX
    Explanations

    capital cities and airport locations

    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_10/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
     всех
    -1.27
     credo
    -1.20
    ,;
    -1.16
    たまに
    -1.10
     magnific
    -1.09
     oltre
    -1.08
     !!!!
    -1.07
    owanych
    -1.07
    WHY
    -1.07
    aturday
    -1.07
    POSITIVE LOGITS
     their
    1.29
     had
    1.27
     still
    1.25
     became
    1.23
     just
    1.22
     at
    1.20
    rası
    1.19
     anoche
    1.15
     using
    1.14
     furthering
    1.14
    Activations Density 0.035%

    No Known Activations