© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 197222
    Prev
    Next
    INDEX
    Explanations

    Perkins should, Wen smiled

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

    Decoding phrases or words

    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
     aras
    0.51
     各
    0.48
     JOURNAL
    0.47
     中心
    0.47
     nField
    0.46
    费用
    0.46
    メイン
    0.46
    スマホ
    0.46
    馕
    0.45
    すると
    0.45
    POSITIVE LOGITS
    δά
    0.44
     deodor
    0.44
    verde
    0.43
     Pflanzen
    0.41
     کھیلنا
    0.41
    ๓
    0.41
     واکنش
    0.41
     окружающей
    0.41
    imbulkan
    0.40
    डर
    0.40
    Activations Density 0.001%

    No Known Activations