© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10978
    Prev
    Next
    INDEX
    Explanations

    international human rights law

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

    human rights

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

    human rights

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
     बैग
    0.47
    퀀
    0.42
    Shake
    0.42
    shake
    0.41
    摇头
    0.41
    qtt
    0.41
     ব্যাগ
    0.40
    ंसू
    0.39
    啃
    0.38
     انف
    0.38
    POSITIVE LOGITS
     Amnesty
    1.00
     Human
    0.98
     মানবাধিকার
    0.96
     human
    0.88
    Human
    0.85
     HUMAN
    0.80
     ह्यूमन
    0.79
     torture
    0.74
     മനു
    0.73
    human
    0.73
    Activations Density 0.160%

    No Known Activations