© 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. 146726
    Prev
    Next
    INDEX
    Explanations

    Nike retailers, years ago

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

    items, player, nautical

    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
     Marke
    0.46
    ?
    0.45
    E
    0.44
    D
    0.42
    Mark
    0.41
    i
    0.41
    rainment
    0.41
    MARK
    0.40
    "][
    0.40
     예정
    0.39
    POSITIVE LOGITS
     trattano
    0.48
     বিশ্ববিদ্যালয়ে
    0.47
    ලය
    0.46
     prioritized
    0.46
    
    0.45
     الوطنية
    0.45
     abogados
    0.45
    发动机
    0.45
    अधिका
    0.45
    зра
    0.44
    Activations Density 0.001%

    No Known Activations