© 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. 70492
    Prev
    Next
    INDEX
    Explanations

    descriptions of journeys and states

    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
    thiết
    -1.57
    抬手
    -1.51
    
    -1.50
     motores
    -1.48
     ordf
    -1.48
    ()`
    -1.47
     fabricado
    -1.46
    </strong>
    -1.46
    
    -1.46
    ...</
    -1.45
    POSITIVE LOGITS
    It
    1.85
    They
    1.80
    “
    1.60
    ]
    1.59
    will
    1.56
     Of
    1.55
     Would
    1.54
     to
    1.52
     But
    1.50
    would
    1.49
    Activations Density 0.107%

    No Known Activations