© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11158
    Prev
    Next
    INDEX
    Explanations

    theory and theoretical

    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_31_width_16k_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
     використання
    0.71
    ियों
    0.70
    ва
    0.63
    ных
    0.63
    да
    0.62
    }$\
    0.61
     desejo
    0.61
     χρήση
    0.61
    𝐝
    0.60
    eux
    0.60
    POSITIVE LOGITS
    Theory
    0.85
     teoria
    0.83
     theory
    0.79
     theories
    0.77
     Theorie
    0.75
     Theoretical
    0.73
    理论
    0.72
     Theories
    0.70
     teoría
    0.69
     théorie
    0.69
    Activations Density 0.041%

    No Known Activations