© 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. 68060
    Prev
    Next
    INDEX
    Explanations

    foreign country names and places

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

    locations and instructions

    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
    𒌉
    0.55
    <unused506>
    0.48
     schließen
    0.48
     цієї
    0.47
     ადგილ
    0.47
     ነገ
    0.47
     końcu
    0.47
     последнее
    0.46
    郅
    0.46
     пъ
    0.46
    POSITIVE LOGITS
    日本では
    0.81
     இந்தியாவில்
    0.74
     বাংলাদেশে
    0.70
     বাংলাদেশের
    0.70
     भारतात
    0.67
     Australia
    0.64
     ประเทศ
    0.63
     Netherlands
    0.62
     Indonesia
    0.59
    বাংলাদেশের
    0.59
    Activations Density 0.428%

    No Known Activations