© 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. 84394
    Prev
    Next
    INDEX
    Explanations

    German articles and Slavic suffixes

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

    July, Reported, Offer

    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
    pro
    0.49
    a
    0.46
    ah
    0.45
    pe
    0.45
    din
    0.45
    rimin
    0.44
     escrito
    0.44
    the
    0.43
    indic
    0.43
    decine
    0.42
    POSITIVE LOGITS
     continuité
    0.47
     পরিস্থিতিতে
    0.46
    ούς
    0.45
    ꩡ
    0.45
     праців
    0.45
     পার্থক্য
    0.43
    সজ্জিত
    0.43
     удалось
    0.43
    路径
    0.43
    үкт
    0.42
    Activations Density 0.000%

    No Known Activations