© 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. 41-GEMMASCOPE-2-RES-262K
    7. 34938
    Prev
    Next
    INDEX
    Explanations

    shoes, Spanish, completing

    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
    된다
    0.37
     lẫn
    0.37
    하였다
    0.34
     huynh
    0.34
     combinations
    0.33
     뜻
    0.33
     höheren
    0.33
     sap
    0.33
     তোলে
    0.33
     `=
    0.32
    POSITIVE LOGITS
     featuring
    0.48
    而且
    0.46
     while
    0.44
     которая
    0.44
     Mentre
    0.43
     enquanto
    0.43
     buscando
    0.42
     Enquanto
    0.42
     with
    0.42
     जिसकी
    0.42
    Activations Density 0.001%

    No Known Activations