© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60023
    Prev
    Next
    INDEX
    Explanations

    carry, carrying, carried

    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_all/layer_41_width_262k_l0_big
    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
    馔
    0.38
    整合
    0.38
    স্তের
    0.38
    обра
    0.36
    স্তে
    0.36
    Frances
    0.36
    motivated
    0.34
    纬
    0.34
    隔离
    0.33
    inée
    0.32
    POSITIVE LOGITS
     carry
    2.55
     carrying
    2.38
    carry
    2.33
     Carry
    2.31
     carries
    2.25
    Carry
    2.22
     Carrying
    2.17
     carried
    2.16
    carrying
    2.06
    携带
    1.97
    Activations Density 0.002%

    No Known Activations