© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40593
    Prev
    Next
    INDEX
    Explanations

    U.S. Department of State

    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_53_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
    WO
    0.39
     Schwarzschild
    0.39
     pans
    0.37
     चक्रवृद्धि
    0.37
    훤
    0.37
    verb
    0.37
    ettle
    0.36
     météor
    0.36
     bibliothèque
    0.36
     библиоте
    0.36
    POSITIVE LOGITS
    Bureau
    0.83
     Bureau
    0.78
    局
    0.68
     BUREAU
    0.63
     Secretary
    0.62
    Secretary
    0.61
     bureaus
    0.59
     Department
    0.57
     Bure
    0.55
    secretary
    0.53
    Activations Density 0.002%

    No Known Activations