© 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. 77864
    Prev
    Next
    INDEX
    Explanations

    safely

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

    Core group formation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Ẻ
    0.51
    ம்
    0.51
    ﺔ
    0.51
     León
    0.49
    ۃ
    0.48
     মেয়েটি
    0.48
    ITÉ
    0.48
    ")}}'
    0.47
    َة
    0.47
    خستان
    0.46
    POSITIVE LOGITS
     mempers
    0.45
    eng
    0.43
     doubling
    0.41
     dáng
    0.41
    i
    0.41
    अनु
    0.40
     sen
    0.39
    ipated
    0.39
     ,'
    0.39
    𝖎
    0.39
    Activations Density 0.000%

    No Known Activations