© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70180
    Prev
    Next
    INDEX
    Explanations

    place names in French

    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
    璆
    -2.13
    觧
    -2.03
    勠
    -2.02
     fournies
    -1.94
    骓
    -1.88
     personnalisées
    -1.88
     rendus
    -1.86
    
    -1.86
    鰾
    -1.82
    …»
    -1.81
    POSITIVE LOGITS
     they
    2.28
    jenige
    1.88
     you
    1.85
     Kenntnis
    1.82
     assumption
    1.80
     emblem
    1.80
     army
    1.73
     Annahme
    1.71
     extent
    1.70
     least
    1.69
    Activations Density 0.003%

    No Known Activations