© 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-65K
    7. 30954
    Prev
    Next
    INDEX
    Explanations

    searching for pairs

    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_65k_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
    肠
    0.46
    wyn
    0.41
    मिली
    0.41
     cellul
    0.38
     маник
    0.38
    净化
    0.38
    сте
    0.38
     apron
    0.38
    缫
    0.37
    pun
    0.37
    POSITIVE LOGITS
     searchValue
    0.60
     찾는
    0.57
     búsqueda
    0.57
     searching
    0.54
     searches
    0.54
     searched
    0.53
     pairings
    0.51
     pairs
    0.50
    查找
    0.50
     Searching
    0.49
    Activations Density 0.088%

    No Known Activations