© 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. 14269
    Prev
    Next
    INDEX
    Explanations

    tradition

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

    deep traditions

    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
     Frequently
    0.42
     MPI
    0.42
     worksheet
    0.42
     certificados
    0.41
    🔍
    0.41
     uploaded
    0.41
     treated
    0.40
     certificado
    0.40
     👀
    0.40
     UBND
    0.40
    POSITIVE LOGITS
     traditions
    0.94
     традиции
    0.93
     परंपरा
    0.81
     tradition
    0.80
     tradiciones
    0.80
    伝統
    0.79
     tradición
    0.78
     tradicion
    0.77
     тради
    0.76
    traditional
    0.74
    Activations Density 0.094%

    No Known Activations