© 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-65K
    7. 47599
    Prev
    Next
    INDEX
    Explanations

    comparisons and relations

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    includes
    0.42
     Helps
    0.42
    ๕
    0.41
    sning
    0.41
    ekkür
    0.41
    但也
    0.39
     অর্থাৎ
    0.39
     Anche
    0.38
    odigd
    0.38
     richiede
    0.38
    POSITIVE LOGITS
     comparable
    0.41
    Considering
    0.40
    와
    0.38
     аналоги
    0.38
     संबंधित
    0.38
    ians
    0.38
    一方面
    0.37
    acak
    0.37
    이
    0.37
    Similar
    0.37
    Activations Density 0.097%

    No Known Activations