© 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. 83078
    Prev
    Next
    INDEX
    Explanations

    case and grammatical markers

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

    multiple languages

    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
     mattered
    0.45
     gained
    0.44
     годах
    0.44
     करावी
    0.44
    -)
    0.42
     করেছিলেন
    0.42
    ได
    0.41
    APPING
    0.41
    DebugTest
    0.41
     দেয়নি
    0.41
    POSITIVE LOGITS
     genellikle
    0.84
     için
    0.78
     yalnızca
    0.76
    은
    0.76
    は
    0.73
    ಗಳು
    0.68
     sadece
    0.68
    에는
    0.68
    ның
    0.68
     önemlidir
    0.66
    Activations Density 0.009%

    No Known Activations