© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21759
    Prev
    Next
    INDEX
    Explanations

    his grandparents

    np_acts-logits-general · gemini-2.5-flash-lite

    understand this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subsets
    0.56
    랜
    0.49
     isoforms
    0.47
     insufficiently
    0.47
     corroborate
    0.45
    क
    0.45
    м
    0.45
    명의
    0.44
     substantiated
    0.44
    越来越多的
    0.43
    POSITIVE LOGITS
     menino
    0.48
     hắn
    0.48
    将军
    0.48
     Sa
    0.47
     preço
    0.46
     quân
    0.46
     ejército
    0.46
     Sơn
    0.45
     เขา
    0.45
     garçon
    0.45
    Activations Density 0.000%

    No Known Activations