© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8816
    Prev
    Next
    INDEX
    Explanations

    controlling program behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     surn
    0.67
     integrantes
    0.61
     statunitense
    0.59
     Си
    0.56
     แถม
    0.55
     Besides
    0.54
     С
    0.54
     porém
    0.54
     И
    0.53
     Х
    0.52
    POSITIVE LOGITS
    必须
    0.64
    有效地
    0.62
    かなり
    0.62
    それを
    0.62
    非常に
    0.61
    创建
    0.61
    给定
    0.60
    它们
    0.59
    帐户
    0.59
    允许
    0.59
    Activations Density 0.005%

    No Known Activations