© 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. 10766
    Prev
    Next
    INDEX
    Explanations

    pro-Iranian coalition against armed groups

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

    Geopolitical conflicts and agreements

    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
     Communism
    0.57
     Czechoslovakia
    0.55
     ১৯৮
    0.54
     ২০১০
    0.52
     СССР
    0.51
     Communists
    0.50
    🎌
    0.50
     소련
    0.49
     ১৯৯
    0.49
    ওলানা
    0.48
    POSITIVE LOGITS
     influencer
    0.66
    网红
    0.65
     vaping
    0.64
     проє
    0.64
     Erdoğan
    0.61
     vape
    0.59
     PUBG
    0.59
     Covid
    0.58
     fintech
    0.58
     Vlog
    0.58
    Activations Density 0.110%

    No Known Activations