© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2298
    Prev
    Next
    INDEX
    Explanations

    Native American cultures and traditions

    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_29_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
     charme
    0.85
     chival
    0.76
     knight
    0.71
     légion
    0.71
    瓒
    0.68
    RefManager
    0.65
     furniture
    0.65
     knights
    0.65
    驢
    0.62
    nics
    0.62
    POSITIVE LOGITS
     Indigenous
    1.53
    Indigenous
    1.46
     Tribal
    1.32
     Elders
    1.25
     indigenous
    1.24
     elders
    1.23
     Tribe
    1.19
     tribal
    1.18
     Native
    1.18
     shaman
    1.17
    Activations Density 0.139%

    No Known Activations