© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3670
    Prev
    Next
    INDEX
    Explanations

    complex concepts and issues

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    义
    0.58
     pathophysiology
    0.52
     polymorphisms
    0.52
     pathologies
    0.50
    '
    0.49
     locis
    0.49
     temples
    0.48
    ’
    0.48
    曰
    0.48
    ਲਾ
    0.48
    POSITIVE LOGITS
     Banyak
    0.66
    c
    0.66
     अनेक
    0.65
    with
    0.64
     WITH
    0.59
    <unused2044>
    0.59
    for
    0.59
     עם
    0.59
     Щ
    0.59
    all
    0.58
    Activations Density 1.211%

    No Known Activations