© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5812
    Prev
    Next
    INDEX
    Explanations

    act of carrying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    ك
    0.71
    ক
    0.52
    ми
    0.51
     settling
    0.51
     घे
    0.49
    ائع
    0.49
     bordering
    0.49
    を図
    0.48
    ם
    0.47
    ल
    0.46
    POSITIVE LOGITS
     carry
    1.16
     carries
    1.14
    carry
    1.08
     Carry
    1.05
    carrying
    1.00
     Carrying
    0.99
     carrying
    0.98
     حمل
    0.95
    携带
    0.95
     taşı
    0.94
    Activations Density 0.110%

    No Known Activations