© 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. 31-GEMMASCOPE-2-RES-262K
    7. 129083
    Prev
    Next
    INDEX
    Explanations

    explaining relationships or contexts

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    jasama
    0.46
    viamente
    0.43
    機能
    0.43
    鬱
    0.43
    ◞
    0.42
    นี่
    0.42
    creen
    0.41
    สามารถ
    0.40
    کار
    0.40
    ustainable
    0.40
    POSITIVE LOGITS
     libros
    0.56
     Biblical
    0.48
     libro
    0.47
     لکھنے
    0.46
     books
    0.46
     القرآن
    0.46
    诵
    0.45
     libri
    0.44
     lettura
    0.44
     textbooks
    0.44
    Activations Density 0.003%

    No Known Activations