© 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. 80198
    Prev
    Next
    INDEX
    Explanations

    packages for installation

    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
     ዋና
    0.70
     네
    0.67
    ICK
    0.64
     ነገር
    0.63
     νέα
    0.62
    anyahu
    0.61
    ERY
    0.60
    the
    0.59
     tarea
    0.59
     февраля
    0.57
    POSITIVE LOGITS
    in
    0.82
    im
    0.79
    ص
    0.73
    ع
    0.71
    ح
    0.66
     for
    0.65
    =[]
    0.62
    است
    0.61
    ä
    0.60
     enregist
    0.59
    Activations Density 0.005%

    No Known Activations