© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10452
    Prev
    Next
    INDEX
    Explanations

    espionage and intelligence gathering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    ೇಕ
    0.93
     Flinders
    0.84
     resistencias
    0.82
     firefighters
    0.78
     arterial
    0.77
     defends
    0.77
     defending
    0.76
    ══
    0.76
    区块
    0.76
     convective
    0.75
    POSITIVE LOGITS
     spy
    2.49
     spying
    2.38
     espionage
    2.35
     spies
    2.24
     Spy
    2.05
    Spy
    2.04
    spy
    1.90
     جاس
    1.77
     surveillance
    1.69
    諜
    1.66
    Activations Density 0.157%

    No Known Activations