© 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. 123830
    Prev
    Next
    INDEX
    Explanations

    places and legal proceedings

    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
    锉
    -1.64
     solche
    -1.33
     違い
    -1.30
     sartén
    -1.24
     poignée
    -1.23
     thinkers
    -1.23
     dommage
    -1.23
     kuu
    -1.22
     כך
    -1.21
     réflé
    -1.21
    POSITIVE LOGITS
    hermosa
    1.36
     to
    1.32
    根据
    1.23
     来
    1.22
    </em>
    1.16
    Награды
    1.15
    Hvad
    1.14
     lørdag
    1.13
    backends
    1.13
    entials
    1.11
    Activations Density 0.013%

    No Known Activations