© 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. 8798
    Prev
    Next
    INDEX
    Explanations

    Australian geographic locations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     फीसद
    0.38
     tincture
    0.37
     caveats
    0.36
     ouvrages
    0.34
     neither
    0.34
     직
    0.34
     σύν
    0.33
     는
    0.32
    neither
    0.32
     শুধ
    0.32
    POSITIVE LOGITS
     Australian
    0.56
    Australian
    0.48
     Australia
    0.48
     ऑस्ट्रेलिया
    0.47
    ऑस्ट्रेलिया
    0.46
    Australia
    0.45
     Австра
    0.45
    澳大利亚
    0.45
    Melbourne
    0.43
     Australien
    0.42
    Activations Density 0.000%

    No Known Activations