© 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. 198740
    Prev
    Next
    INDEX
    Explanations

    capital 'P'

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

    title and 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
    大佬
    0.49
     exhib
    0.44
     snowflakes
    0.44
     examen
    0.44
    这话
    0.43
    试试
    0.42
     sév
    0.42
     flotte
    0.42
    伪
    0.42
     accueill
    0.41
    POSITIVE LOGITS
    \_
    0.52
    a
    0.52
    薦
    0.49
    cheid
    0.48
    種類の
    0.46
    m
    0.45
    becomes
    0.45
     Describes
    0.45
     ኮ
    0.44
    westen
    0.44
    Activations Density 0.000%

    No Known Activations