© 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. 146564
    Prev
    Next
    INDEX
    Explanations

    specifiers and foreign words

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

    funding, response, delivery

    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
     lamented
    0.45
     unusually
    0.43
    醗
    0.40
    МУ
    0.38
     sings
    0.38
     writes
    0.38
     unkind
    0.38
    ኅ
    0.38
    ху
    0.37
     ঊ
    0.37
    POSITIVE LOGITS
    فيد
    0.49
    ترنت
    0.46
     debemos
    0.45
     الحصول
    0.45
     لدينا
    0.45
     tengamos
    0.45
     الحل
    0.44
     تطبيق
    0.44
     permite
    0.44
     duis
    0.44
    Activations Density 0.000%

    No Known Activations