© 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. 34-GEMMASCOPE-RES-131K
    4. 90948
    Prev
    Next
    INDEX
    Explanations

    it all

    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
     einfachen
    -0.97
     solchen
    -0.94
     gleichen
    -0.94
     entsprechenden
    -0.94
     bestimmten
    -0.92
     bestehenden
    -0.91
     größeren
    -0.91
     are
    -0.91
     aktuellen
    -0.89
     klassischen
    -0.88
    POSITIVE LOGITS
     all
    4.38
     جميع
    2.56
     semua
    2.27
     всех
    2.02
     همه
    2.00
     allemaal
    1.98
     wszystkich
    1.95
     всички
    1.88
    すべて
    1.87
     kaikki
    1.87
    Activations Density 0.029%

    No Known Activations