© 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. 220957
    Prev
    Next
    INDEX
    Explanations

    foreign markets and competition

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

    object detection

    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
    ピンク
    0.53
    टी
    0.52
    ट्टा
    0.52
    ローブ
    0.51
    자동차
    0.50
     partying
    0.49
    티
    0.49
    இந்திய
    0.49
    क्राफ्ट
    0.48
    洵
    0.48
    POSITIVE LOGITS
     בן
    0.48
    reliant
    0.46
    inating
    0.46
     רבים
    0.44
    reliance
    0.44
    赋
    0.43
     MD
    0.43
     наде
    0.42
     נפ
    0.42
     Reliance
    0.41
    Activations Density 0.000%

    No Known Activations