© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65347
    Prev
    Next
    INDEX
    Explanations

    country names and nationalities

    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
    dé
    -1.14
    8
    -1.10
    sel
    -1.10
    葩
    -1.09
     düşün
    -1.09
     altri
    -1.09
     gos
    -1.08
     Bagaimana
    -1.05
    zzel
    -1.05
     GeoNames
    -1.05
    POSITIVE LOGITS
    ],
    1.42
    不已
    1.38
     their
    1.37
     Tasks
    1.30
     informaciones
    1.29
     eikä
    1.28
    toluene
    1.27
    eater
    1.27
    рії
    1.23
    sikker
    1.23
    Activations Density 0.030%

    No Known Activations