© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66301
    Prev
    Next
    INDEX
    Explanations

    Russian and Russian text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ར་
    -0.93
    bowler
    -0.86
     Ihe
    -0.85
     गरे
    -0.84
    noah
    -0.81
     theologians
    -0.79
     shortcomings
    -0.77
    circulation
    -0.77
    مكن
    -0.76
    conditionally
    -0.76
    POSITIVE LOGITS
     Russian
    1.14
     Russians
    1.06
     Russia
    0.90
     ru
    0.90
    Russian
    0.90
    Russia
    0.88
     Moscow
    0.87
     ruso
    0.85
    uatu
    0.85
     rs
    0.82
    Activations Density 0.023%

    No Known Activations