© 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. 47466
    Prev
    Next
    INDEX
    Explanations

    past events and studies

    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
     بالإضافة
    -2.59
    艫
    -2.52
     เรา
    -2.52
     ใน
    -2.42
     нового
    -2.38
    の方に
    -2.34
     literalmente
    -2.34
    辚
    -2.31
    缡
    -2.31
     teknologi
    -2.28
    POSITIVE LOGITS
     innumerable
    2.80
    o
    2.73
     numerous
    2.72
    تیجه
    2.59
     this
    2.58
     Vordergrund
    2.58
    𓆟
    2.58
     impeccable
    2.50
    ྜ
    2.44
     embro
    2.39
    Activations Density 0.008%

    No Known Activations