© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63461
    Prev
    Next
    INDEX
    Explanations

    Join us

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

    Hook/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
    Negative Logits
     called
    0.45
     \
    0.43
    k
    0.42
     memories
    0.42
     constellations
    0.42
     words
    0.42
     twist
    0.42
     speeches
    0.41
     throughout
    0.41
     Canon
    0.41
    POSITIVE LOGITS
    മിതി
    0.50
    എം
    0.50
     اذا
    0.50
    ഗോ
    0.49
    ătoare
    0.49
    基础设施
    0.49
    INDUSTRIAL
    0.48
    𒀊
    0.48
     අපි
    0.48
     عند
    0.48
    Activations Density 0.000%

    No Known Activations