© 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. 55510
    Prev
    Next
    INDEX
    Explanations

    geopolitical or abstract concepts

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

    felt lucky

    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
    铭
    0.56
    그리고
    0.52
     하지만
    0.52
    둬
    0.51
     لكن
    0.51
     سیستم
    0.50
    ająca
    0.50
    营收
    0.50
     그리고
    0.50
    辂
    0.50
    POSITIVE LOGITS
     theses
    0.57
     conflicts
    0.46
     phenomena
    0.45
     vortices
    0.45
     separatist
    0.45
     provinces
    0.44
     hypothesize
    0.43
     colonial
    0.43
     continents
    0.43
     extremist
    0.43
    Activations Density 0.000%

    No Known Activations