© 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. 22-GEMMASCOPE-RES-131K
    7. 13087
    Prev
    Next
    INDEX
    Explanations

    cities, counties, districts, and governments

    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
     Inſ
    -1.28
    CAPITULO
    -1.19
     marav
    -1.18
     Reſ
    -1.17
     isolado
    -1.16
    Доброго
    -1.15
    Добрый
    -1.15
     Audiodateien
    -1.14
     Conſ
    -1.14
    Máy
    -1.13
    POSITIVE LOGITS
     government
    1.40
     both
    1.39
     governments
    1.30
     on
    1.21
     politiker
    1.17
     authorities
    1.12
     plans
    1.09
     Government
    1.05
     politicians
    1.05
     of
    1.02
    Activations Density 0.029%

    No Known Activations