© 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. 55999
    Prev
    Next
    INDEX
    Explanations

    occurred millennia ago

    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
    轵
    0.48
    ﺪ
    0.45
    د
    0.44
    اته
    0.43
     Função
    0.42
    無料
    0.42
     شخصی
    0.42
     ！
    0.41
    ر
    0.41
    睃
    0.41
    POSITIVE LOGITS
     outspoken
    0.54
     relocate
    0.50
     oars
    0.49
     rescues
    0.48
     relocated
    0.48
     outnumbered
    0.48
     electronics
    0.47
     reorganized
    0.46
     ventilators
    0.45
     outfitted
    0.45
    Activations Density 0.001%

    No Known Activations