© 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. 22-GEMMASCOPE-RES-131K
    4. 104465
    Prev
    Next
    INDEX
    Explanations

    countries clash

    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_22/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
     mắn
    -1.33
     should
    -1.22
    ológia
    -1.20
     сайта
    -1.16
     often
    -1.13
    IMENTO
    -1.13
     часто
    -1.13
     may
    -1.11
     merece
    -1.11
     často
    -1.10
    POSITIVE LOGITS
    ってない
    1.23
     there
    1.20
     стене
    1.20
     выпе
    1.11
     vélos
    1.09
    各个
    1.08
     Âge
    1.08
     hôtels
    1.07
     vinho
    1.07
     citizens
    1.07
    Activations Density 0.054%

    No Known Activations