© 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. 85871
    Prev
    Next
    INDEX
    Explanations

    listed classes

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

    Docker, sweater, golden, command, Polish, burns

    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
    티브
    0.53
    벨
    0.52
    벵
    0.50
    여행
    0.49
    냈다
    0.49
    |।
    0.48
    लीटर
    0.47
    였다
    0.47
    畯
    0.47
    |.|.|
    0.47
    POSITIVE LOGITS
     productService
    0.50
     אס
    0.46
     đổi
    0.46
     ಮೆ
    0.46
    Promise
    0.43
    Elect
    0.43
    ának
    0.43
     contentService
    0.43
    Spain
    0.41
     مع
    0.41
    Activations Density 0.000%

    No Known Activations