© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4498
    Prev
    Next
    INDEX
    Explanations

    war, military, soldiers, combat

    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_40_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
     पालिका
    0.43
     CSV
    0.40
    拗
    0.40
     cowork
    0.39
     coworking
    0.39
     Airbnb
    0.38
     appartement
    0.38
    шеб
    0.38
     Mathematica
    0.38
    🏡
    0.38
    POSITIVE LOGITS
     military
    1.58
     battlefield
    1.54
     warfare
    1.53
     soldiers
    1.52
    战争
    1.47
    战场
    1.45
    士兵
    1.44
     전쟁
    1.44
    military
    1.42
     전투
    1.42
    Activations Density 0.048%

    No Known Activations