© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252626
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    医学
    0.54
     मेडिकल
    0.53
     pharmaceut
    0.52
    医
    0.50
     भरोसा
    0.50
    医疗
    0.49
     bilmi
    0.49
    hWnd
    0.49
    भु
    0.48
     exercitation
    0.48
    POSITIVE LOGITS
    -
    0.39
    Increased
    0.38
     הז
    0.37
     cualquiera
    0.36
    Circular
    0.36
    গুলিকে
    0.36
    Executive
    0.35
     cadenas
    0.35
     Increase
    0.35
     అయితే
    0.34
    Activations Density 0.005%

    No Known Activations