© 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. 10-GEMMASCOPE-RES-131K
    4. 130256
    Prev
    Next
    INDEX
    Explanations

    size

    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
     kien
    -1.64
     octavo
    -1.53
     natale
    -1.50
    de
    -1.47
    Dès
    -1.46
     There
    -1.44
     techo
    -1.44
    ztes
    -1.42
    蕯
    -1.39
    si
    -1.38
    POSITIVE LOGITS
    ambut
    1.78
     gäng
    1.77
     Erwartungen
    1.76
     serán
    1.76
     Beobachtungen
    1.72
     utilisée
    1.71
     Verständ
    1.66
     cukru
    1.65
     alkoholu
    1.64
     Veränderungen
    1.62
    Activations Density 0.019%

    No Known Activations