© 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-262K
    7. 130076
    Prev
    Next
    INDEX
    Explanations

    merges and combines

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    тті
    0.43
    North
    0.42
    improve
    0.39
    احنا
    0.39
    ႏ
    0.38
    Вы
    0.38
    Мы
    0.38
    ريم
    0.38
     북
    0.37
    噻
    0.37
    POSITIVE LOGITS
     merges
    0.61
     merged
    0.57
     merging
    0.54
     merger
    0.52
    Merged
    0.48
     merge
    0.48
     amalgam
    0.45
     added
    0.44
    merged
    0.44
     mergers
    0.43
    Activations Density 0.001%

    No Known Activations