© 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. 48477
    Prev
    Next
    INDEX
    Explanations

    currency and timezone abbreviations

    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
     другие
    -1.68
     then
    -1.68
     others
    -1.62
     other
    -1.56
     cueva
    -1.55
     []:
    -1.53
     함께
    -1.50
    __(/*!
    -1.47
    ().__
    -1.45
     други
    -1.45
    POSITIVE LOGITS
     После
    1.66
    Significado
    1.51
     ausdrück
    1.47
     solchen
    1.43
     takiego
    1.43
     Когда
    1.41
     superstars
    1.34
     desarrollar
    1.30
     Could
    1.27
     equivalent
    1.26
    Activations Density 0.038%

    No Known Activations