© 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. 104991
    Prev
    Next
    INDEX
    Explanations

    wish to have

    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
     Yet
    -1.90
     need
    -1.83
     amenaz
    -1.56
     requieren
    -1.52
     The
    -1.43
    cheidet
    -1.40
    }.
    -1.35
     Añade
    -1.34
     Instead
    -1.33
     tendrán
    -1.33
    POSITIVE LOGITS
    Опис
    1.62
     達
    1.54
    ケ
    1.45
     anonyme
    1.41
    ercizi
    1.40
     and
    1.38
     SPANISH
    1.37
    ֙
    1.37
    ヘ
    1.37
    体的
    1.36
    Activations Density 0.038%

    No Known Activations