© 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. 18780
    Prev
    Next
    INDEX
    Explanations

    international conflict and capabilities

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

    focusing on getting

    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
     Quận
    0.45
    无
    0.43
    ۔
    0.43
     dân
    0.42
    脸
    0.42
    The
    0.42
     Contempor
    0.42
     द
    0.41
    民间
    0.41
    宪
    0.41
    POSITIVE LOGITS
     intensifying
    0.55
     revanche
    0.47
     ಮತ್ತೆ
    0.47
     выигра
    0.47
     erneut
    0.46
     defeating
    0.46
     kembali
    0.45
     reprogram
    0.45
     intensify
    0.45
    ঙ্কা
    0.45
    Activations Density 0.000%

    No Known Activations