© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2406
    Prev
    Next
    INDEX
    Explanations

    Russian and other Slavic words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    Een
    1.04
     signalé
    1.04
    ような
    0.92
     gratu
    0.92
     moins
    0.91
     dernier
    0.90
    </div>
    0.88
     trouva
    0.88
     bleue
    0.88
     obtenu
    0.87
    POSITIVE LOGITS
    d
    1.06
    ק
    0.96
    د
    0.90
    ни
    0.81
    ع
    0.81
    ้ม
    0.80
    g
    0.79
    rę
    0.79
    ка
    0.76
    นด์
    0.75
    Activations Density 0.002%

    No Known Activations