© 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. 10130
    Prev
    Next
    INDEX
    Explanations

    World War I events

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

    World War I and aftermath

    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
    フライ
    0.47
    kinawa
    0.46
    昭和
    0.46
     СССР
    0.44
     ১৯৬৫
    0.44
     ১৯৬
    0.44
    藏
    0.43
    台北
    0.41
     ಒಳಗ
    0.41
     Reagan
    0.40
    POSITIVE LOGITS
     trenches
    0.88
     trench
    0.87
     Trench
    0.74
     Austro
    0.66
     Germans
    0.66
     German
    0.64
     Verdun
    0.64
     Weltkrieg
    0.63
     influenza
    0.61
     Tren
    0.61
    Activations Density 0.117%

    No Known Activations