© 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. 104481
    Prev
    Next
    INDEX
    Explanations

    .com websites

    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
     Anhänger
    -1.22
     oleh
    -1.22
     a
    -1.21
     grossen
    -1.17
     dom
    -1.17
    +"_
    -1.15
     ricas
    -1.14
     größeren
    -1.11
     an
    -1.09
    ování
    -1.09
    POSITIVE LOGITS
     münchen
    1.34
     verhind
    1.27
     nogal
    1.25
     zeven
    1.25
     nimmer
    1.25
     spiegel
    1.23
     verminder
    1.23
    geladen
    1.23
     schen
    1.23
     harte
    1.23
    Activations Density 0.031%

    No Known Activations