© 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. 81065
    Prev
    Next
    INDEX
    Explanations

    ling-based words, linguists, language

    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
     gelap
    -0.85
    ائدة
    -0.85
     rips
    -0.81
     mirip
    -0.77
     chert
    -0.76
     Lait
    -0.76
    ර
    -0.75
     corporal
    -0.75
    uden
    -0.75
    Drinks
    -0.70
    POSITIVE LOGITS
    afel
    1.06
     Ling
    1.06
    ling
    0.92
     ling
    0.91
    ering
    0.89
    乾隆
    0.89
    Ling
    0.80
    elser
    0.77
    sih
    0.77
     dizendo
    0.77
    Activations Density 0.012%

    No Known Activations