© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48127
    Prev
    Next
    INDEX
    Explanations

    human rights violations and abuses

    np_acts-logits-general · gemini-2.5-flash-lite

    human rights advocacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     বিস্ফো
    0.49
     ভূমিকম্প
    0.45
    🐡
    0.45
    camouflage
    0.43
    Antae
    0.43
    शल
    0.43
    窯
    0.43
    鸥
    0.43
     ईंधन
    0.42
    二维码
    0.42
    POSITIVE LOGITS
     মানবাধিকার
    0.96
     Amnesty
    0.82
     Human
    0.72
     Rights
    0.64
     নির্যাতন
    0.63
     മനു
    0.63
     decriminal
    0.61
     HUMAN
    0.61
     ICRC
    0.60
    Human
    0.59
    Activations Density 0.068%

    No Known Activations