© 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. 10-GEMMASCOPE-RES-131K
    7. 123757
    Prev
    Next
    INDEX
    Explanations

    prevalence and percentages

    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_10/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
     Sekarang
    -1.66
     parlar
    -1.66
     Anggota
    -1.63
     Lokasi
    -1.61
     wijze
    -1.59
    ťaž
    -1.57
    oré
    -1.57
     Keuangan
    -1.56
     milyen
    -1.55
     abband
    -1.53
    POSITIVE LOGITS
     (
    1.77
     gdyż
    1.74
     "
    1.72
     a
    1.70
     
    1.66
    (
    1.65
     '
    1.61
    "
    1.56
     بنابراین
    1.52
     to
    1.52
    Activations Density 0.085%

    No Known Activations