© 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. 11162
    Prev
    Next
    INDEX
    Explanations

    United States and its allies

    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
     Mereka
    -1.10
     Our
    -1.09
    tarta
    -1.08
     его
    -1.06
     où
    -1.04
     by
    -1.01
     Menurut
    -1.00
     Sekarang
    -0.99
     даже
    -0.98
    我们的
    -0.98
    POSITIVE LOGITS
     partea
    1.13
     obicei
    1.11
     gettyimages
    1.11
     MATHEMAT
    1.05
     rosario
    1.03
     Hygge
    1.02
     cauza
    1.01
     echip
    1.01
    GRAFÍA
    1.00
     "\<
    1.00
    Activations Density 0.069%

    No Known Activations