© 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. 215959
    Prev
    Next
    INDEX
    Explanations

    metallic gold printing

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

    contrasting words or errors

    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
     miesią
    0.60
     wszystkich
    0.54
     მხოლოდ
    0.54
     каждой
    0.53
     必ず
    0.52
     Конечно
    0.50
     ലഭ്യ
    0.50
    ௦
    0.50
     ഇനി
    0.49
    szyst
    0.49
    POSITIVE LOGITS
    panic
    0.50
    سب
    0.45
    पे
    0.45
    opin
    0.44
    c
    0.43
    पी
    0.42
    config
    0.42
    adapter
    0.42
    markup
    0.42
    requirements
    0.42
    Activations Density 0.000%

    No Known Activations