© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85278
    Prev
    Next
    INDEX
    Explanations

    state car, sales, crochet, provisions, iron

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

    Robot Restaurant

    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
    Negative Logits
     disfraz
    0.45
    的发
    0.45
     Chemicals
    0.45
    陡
    0.44
     probado
    0.44
    潭
    0.44
    வே
    0.44
    dit
    0.43
    肠
    0.43
    挠
    0.43
    POSITIVE LOGITS
     優
    0.48
     rctx
    0.47
     yks
    0.47
     vän
    0.42
    屬於
    0.41
     umož
    0.40
     প্রতিক্রিয়া
    0.39
    ઠવા
    0.39
     Korea
    0.38
     sumar
    0.38
    Activations Density 0.001%

    No Known Activations