© 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. 215619
    Prev
    Next
    INDEX
    Explanations

    keywords and their consequences

    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
    氾
    0.47
     ਸ਼
    0.38
    涿
    0.38
    ̺
    0.38
     believer
    0.38
     를
    0.37
    計測
    0.37
     مقدار
    0.37
     أو
    0.36
     won
    0.36
    POSITIVE LOGITS
    律
    0.42
    clus
    0.38
     separable
    0.38
     সাক্ষাৎ
    0.38
    wards
    0.37
     পরম্প
    0.37
    hedge
    0.36
    rook
    0.36
    SMITH
    0.35
    radu
    0.35
    Activations Density 0.000%

    No Known Activations