© 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. 131028
    Prev
    Next
    INDEX
    Explanations

    national security and government surveillance

    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
     también
    -1.48
     also
    -1.48
     Makanan
    -1.37
     Empfindung
    -1.33
     También
    -1.30
     også
    -1.23
    timberland
    -1.23
    普及
    -1.20
    TÜ
    -1.20
     Meningkatkan
    -1.19
    POSITIVE LOGITS
    LYPH
    1.26
     ponemos
    1.12
    }};
    1.12
    様々
    1.09
     yesterday
    1.09
    vez
    1.09
    actic
    1.08
     администрации
    1.08
    iate
    1.06
     anschließend
    1.06
    Activations Density 0.142%

    No Known Activations