© 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. 70541
    Prev
    Next
    INDEX
    Explanations

    Macron and France

    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
     but
    -2.09
     to
    -1.53
    를
    -1.41
     quindi
    -1.39
     angewendet
    -1.35
     bolj
    -1.27
     as
    -1.27
     reduzieren
    -1.21
     WITHOUT
    -1.20
    vols
    -1.19
    POSITIVE LOGITS
     >",
    1.30
    jarse
    1.20
     trovi
    1.17
     if
    1.11
    èvement
    1.09
    бен
    1.09
     telt
    1.08
    
    1.07
    tidase
    1.07
     け
    1.06
    Activations Density 0.031%

    No Known Activations