© 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. 31-GEMMASCOPE-2-RES-262K
    7. 18898
    Prev
    Next
    INDEX
    Explanations

    collapse of the Soviet Union and Russia

    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_31_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
     eSIM
    0.47
    ές
    0.46
     दशमलव
    0.44
    Rés
    0.44
     GraphQL
    0.42
     Recharge
    0.41
     Reap
    0.41
    鸢
    0.41
    额外的
    0.41
    龟
    0.41
    POSITIVE LOGITS
     Russian
    0.63
     russia
    0.61
     Rusia
    0.59
     Russia
    0.59
    ロシア
    0.59
     러시아
    0.58
     Soviet
    0.55
     russian
    0.54
     sovi
    0.54
     روسیه
    0.53
    Activations Density 0.022%

    No Known Activations