© 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. 47596
    Prev
    Next
    INDEX
    Explanations

    international associations and specific 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
     նաև
    -1.50
     is
    -1.38
     even
    -1.28
    大阪府
    -1.27
    Дере
    -1.25
     to
    -1.24
     (
    -1.22
     һәм
    -1.20
     gradova
    -1.20
     nalazi
    -1.19
    POSITIVE LOGITS
     ............
    1.26
    鬭
    1.25
     pocos
    1.24
     Scritto
    1.23
     detayl
    1.23
     wenn
    1.23
    噩
    1.23
     faltan
    1.21
    膘
    1.20
    kops
    1.20
    Activations Density 0.077%

    No Known Activations