© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11098
    Prev
    Next
    INDEX
    Explanations

    attack and invasion

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

    invasion and war

    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_40_width_16k_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
    acf
    0.48
    tracker
    0.44
    ="@
    0.43
    vcx
    0.43
    caught
    0.42
     wartime
    0.41
     rivalry
    0.40
    opponent
    0.40
    斗
    0.40
    SplashScreen
    0.40
    POSITIVE LOGITS
     invasion
    2.00
     invade
    1.84
     invasions
    1.83
     Invasion
    1.80
    invasion
    1.75
     invas
    1.69
     invading
    1.69
     invaded
    1.64
    invas
    1.58
    侵
    1.48
    Activations Density 0.177%

    No Known Activations