© 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. 243852
    Prev
    Next
    INDEX
    Explanations

    specific context or noun introduction

    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
     at
    0.61
     to
    0.50
    ਵ
    0.48
    ven
    0.46
     picture
    0.46
     convince
    0.46
    بازی
    0.46
     thrive
    0.45
    জ
    0.45
     affect
    0.45
    POSITIVE LOGITS
     তৃত
    0.50
    টে
    0.49
     빼
    0.49
     সম্পূর্ন
    0.49
     MFP
    0.49
    껭
    0.47
     Zeitschr
    0.47
     MIF
    0.47
     계약
    0.47
     Simplifying
    0.46
    Activations Density 0.001%

    No Known Activations