© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12459
    Prev
    Next
    INDEX
    Explanations

    major and key items

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    exactly
    0.43
    Luxury
    0.42
     tudo
    0.41
     esattamente
    0.41
    缜
    0.41
     Everything
    0.40
    Everything
    0.40
    everything
    0.39
     combinación
    0.39
    왤
    0.38
    POSITIVE LOGITS
     주요
    1.76
    主要的
    1.52
     प्रमुख
    1.49
     notable
    1.45
    主要
    1.42
     основных
    1.41
    主な
    1.41
    的主要
    1.38
     major
    1.37
     основные
    1.34
    Activations Density 1.523%

    No Known Activations