© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55631
    Prev
    Next
    INDEX
    Explanations

    intelligence, espionage, and spying

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

    intelligence espionage gathering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    டோ
    0.49
    荭
    0.45
     quadrat
    0.43
     सीएचसी
    0.43
    鳝
    0.43
     சுற்றுச்சூழ
    0.43
    র্ব
    0.42
    év
    0.42
     Cane
    0.42
     invo
    0.42
    POSITIVE LOGITS
     espionage
    1.36
     intelligence
    1.30
     spying
    1.30
     Intelligence
    1.27
     खुफिया
    1.27
    intelligence
    1.25
     spy
    1.23
     spies
    1.23
    Intelligence
    1.22
    諜
    1.05
    Activations Density 0.099%

    No Known Activations