© 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. 38026
    Prev
    Next
    INDEX
    Explanations

    foreign words and structured 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
     segü
    -0.97
    oane
    -0.89
    leis
    -0.87
    kı
    -0.87
    diente
    -0.87
     macam
    -0.86
    pezif
    -0.84
     COMPOUNDS
    -0.83
     الموقع
    -0.83
    ‎
    -0.83
    POSITIVE LOGITS
    马逊
    0.92
     Wikiseite
    0.91
     teilweise
    0.86
     nyní
    0.85
    半个
    0.85
     ahora
    0.83
    importante
    0.82
     sayuran
    0.82
    Groet
    0.82
     entweder
    0.82
    Activations Density 0.061%

    No Known Activations