© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8490
    Prev
    Next
    INDEX
    Explanations

    London and Paris

    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
     they
    -2.03
    4
    -1.75
    being
    -1.65
     that
    -1.60
     '\\;'
    -1.60
    最重要的
    -1.55
    mates
    -1.50
    ine
    -1.50
    3
    -1.46
     like
    -1.45
    POSITIVE LOGITS
    低声
    1.55
    将他
    1.45
     provocando
    1.38
    骤
    1.36
     causando
    1.35
    かもし
    1.33
    当即
    1.33
     efectu
    1.30
    ạy
    1.30
    GERS
    1.29
    Activations Density 0.205%

    No Known Activations