© 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. 129825
    Prev
    Next
    INDEX
    Explanations

    however, year, men, sacrifice, offered, opposed, practice, importantly

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

    blueprints, runner, difficult, chase

    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
     construcción
    0.52
     are
    0.51
    िप्ट
    0.46
     이제
    0.46
     campos
    0.44
    ভাষা
    0.44
    νά
    0.44
    ４
    0.44
    🚅
    0.43
    你自己
    0.43
    POSITIVE LOGITS
     सहमत
    0.44
    參加
    0.43
     العلمي
    0.42
     सालाना
    0.41
     त्याचा
    0.41
     uczest
    0.41
    参加
    0.40
     رفض
    0.40
     convain
    0.40
     उंची
    0.40
    Activations Density 0.002%

    No Known Activations