© 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-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 35194
    Prev
    Next
    INDEX
    Explanations

    spy, agent, secret service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     herd
    0.45
     দৈত্য
    0.45
     migrate
    0.40
     weld
    0.40
    喳
    0.39
    㖑
    0.39
     गोबर
    0.39
    벅
    0.39
     ぞ
    0.38
    㝅
    0.38
    POSITIVE LOGITS
     spy
    1.88
     espionage
    1.81
     spies
    1.74
    spy
    1.51
     Spy
    1.48
     agent
    1.45
     agents
    1.45
     spying
    1.45
     Agent
    1.42
    Spy
    1.42
    Activations Density 0.042%

    No Known Activations