© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17208
    Prev
    Next
    INDEX
    Explanations

    covert operations and guerrilla tactics

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

    covert infiltration and raids

    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_53_width_65k_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
    军
    0.56
     군
    0.49
    軍
    0.48
     stationed
    0.48
    군의
    0.47
     army
    0.45
    军队
    0.45
    군
    0.44
     ADMINISTRATION
    0.44
    army
    0.43
    POSITIVE LOGITS
     guerrilla
    1.18
     guer
    1.07
     Guerr
    1.02
     comm
    1.02
     guerr
    1.02
     covert
    0.94
     sabotage
    0.91
     Guer
    0.91
     irregular
    0.91
     raiding
    0.88
    Activations Density 0.056%

    No Known Activations