© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141397
    Prev
    Next
    INDEX
    Explanations

    institutional roles

    np_acts-logits-general · gemini-2.5-flash-lite

    correct classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     booked
    0.48
    originals
    0.45
     التاريخ
    0.44
    می
    0.43
     eventualmente
    0.43
     رپور
    0.42
    مرات
    0.42
    ؏
    0.42
     incurring
    0.41
    时间
    0.41
    POSITIVE LOGITS
    禣
    0.51
    薁
    0.44
     defrost
    0.43
     किचन
    0.43
     Compagnie
    0.43
    Ware
    0.41
    ucht
    0.41
     помогает
    0.41
     mascul
    0.41
     Шрифт
    0.41
    Activations Density 0.001%

    No Known Activations