© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1273
    Prev
    Next
    INDEX
    Explanations

    systemic racism, onclick, OpenGL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
    יות
    1.78
    ﺢ
    1.77
    рија
    1.66
    ட்சத்திர
    1.57
    ت
    1.56
     parado
    1.54
    睗
    1.49
     Aucun
    1.48
     umur
    1.47
    tss
    1.47
    POSITIVE LOGITS
    at
    1.98
    щики
    1.96
    з
    1.94
    ين
    1.88
    in
    1.81
    শ
    1.81
    ার
    1.71
    пер
    1.66
     насеко
    1.66
     thí
    1.63
    Activations Density 0.528%

    No Known Activations