© 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. 22-GEMMASCOPE-RES-131K
    4. 66768
    Prev
    Next
    INDEX
    Explanations

    hypothetical or expected outcomes

    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_22/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
     exacto
    -0.97
    Apenas
    -0.84
     sometimes
    -0.84
     может
    -0.83
    פשר
    -0.81
    Sejarah
    -0.79
     can
    -0.78
    Благодаря
    -0.78
     vinyle
    -0.78
     теперь
    -0.77
    POSITIVE LOGITS
     would
    1.62
    would
    1.29
    Would
    1.14
     gdyby
    1.04
     tendría
    1.04
    wouldn
    1.03
     wouldn
    0.94
     visible
    0.94
     Would
    0.94
     widać
    0.93
    Activations Density 0.018%

    No Known Activations