© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9530
    Prev
    Next
    INDEX
    Explanations

    Russian prefix "за-"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amalgamation
    0.39
    स्परिक
    0.39
     hommage
    0.38
     pembahasan
    0.38
     newdata
    0.38
     homage
    0.38
     mandate
    0.37
    슭
    0.37
    ασίας
    0.37
     ital
    0.37
    POSITIVE LOGITS
     исключением
    0.48
    За
    0.43
    pick
    0.42
     основу
    0.41
    Breaking
    0.41
    ht
    0.40
    Todo
    0.40
     заг
    0.40
    todo
    0.39
    бав
    0.39
    Activations Density 0.041%

    No Known Activations