© 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. 119722
    Prev
    Next
    INDEX
    Explanations

    national security and defense

    np_acts-logits-general · gemini-2.5-flash-lite

    references to national security, defense, and strategic military or governmental matters.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     Waktu
    -1.48
     Ternyata
    -1.46
     Bagaimana
    -1.45
     Tetapi
    -1.44
     Misalnya
    -1.43
     Terbaru
    -1.43
     Kondisi
    -1.43
    Ruju
    -1.42
     Mungkin
    -1.42
     Manfaat
    -1.41
    POSITIVE LOGITS
     and
    1.83
     a
    1.81
    4
    1.64
    1.61
     I
    1.49
    ↵
    1.46
     not
    1.44
     if
    1.42
    ↵↵↵↵
    1.38
    3
    1.36
    Activations Density 0.038%

    No Known Activations