© 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. 195472
    Prev
    Next
    INDEX
    Explanations

    Slavic language endings

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

    Russian/Ukrainian suffixes

    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
    の
    0.68
    의
    0.63
     and
    0.57
    的
    0.55
     и
    0.54
     و
    0.50
     szt
    0.48
    に
    0.48
    ப்
    0.47
    :
    0.47
    POSITIVE LOGITS
     quarterback
    0.50
     وزیراعظم
    0.47
    alakip
    0.47
    ópez
    0.46
    ementerian
    0.44
     Pemerintah
    0.43
     चैंपियन
    0.42
     الحكومة
    0.42
     curviliné
    0.42
     বিশ্বকাপ
    0.42
    Activations Density 0.001%

    No Known Activations