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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212021
    Prev
    Next
    INDEX
    Explanations

    Russian words starting with Э

    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_262k_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
     propia
    0.38
    Он
    0.38
    Nik
    0.37
     avanzando
    0.37
    ished
    0.37
    鎊
    0.37
    पण
    0.36
    פת
    0.36
    λλ
    0.35
    ωση
    0.35
    POSITIVE LOGITS
     swarm
    0.39
     ঝ
    0.39
    emphasis
    0.38
    pio
    0.37
     foam
    0.36
     emphasis
    0.36
    ревнова
    0.36
     fø
    0.35
     ember
    0.35
     нужда
    0.35
    Activations Density 0.001%

    No Known Activations