© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84605
    Prev
    Next
    INDEX
    Explanations

    license and legal terms

    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
    ждую
    -0.83
    Restore
    -0.81
     Restore
    -0.72
     short
    -0.69
     zás
    -0.65
    عب
    -0.64
     Short
    -0.64
     Groot
    -0.63
     المط
    -0.63
     restore
    -0.62
    POSITIVE LOGITS
     Gub
    0.75
     MEXICO
    0.71
     Divided
    0.70
    lichung
    0.69
    Splitter
    0.69
    řen
    0.69
    薗
    0.68
    semin
    0.67
     Heaton
    0.67
    quo
    0.67
    Activations Density 0.096%

    No Known Activations