© 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. 8604
    Prev
    Next
    INDEX
    Explanations

    war and conflict

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

    war and conflict

    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
     杨
    0.62
     அலுவலக
    0.62
    保养
    0.61
    篱
    0.61
    ранже
    0.57
     Mạnh
    0.57
     చక్కెర
    0.56
     ንጥረ
    0.56
     Développement
    0.56
    镁
    0.56
    POSITIVE LOGITS
     war
    1.53
    戰爭
    1.51
     전쟁
    1.49
     guerra
    1.43
     война
    1.39
    戦争
    1.39
     युद्ध
    1.38
     battlefield
    1.37
     oorlog
    1.36
     guerre
    1.34
    Activations Density 0.105%

    No Known Activations