© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1588
    Prev
    Next
    INDEX
    Explanations

    closing `]]` then

    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
    !=
    -1.76
     to
    -1.75
    Gbps
    -1.66
    
    -1.60
     麦
    -1.60
     februar
    -1.59
     priva
    -1.59
    нули
    -1.59
     territ
    -1.57
     reputa
    -1.56
    POSITIVE LOGITS
     metálico
    2.05
     znajdziesz
    1.91
     мы
    1.90
     naszego
    1.85
     naše
    1.82
     dzisiaj
    1.80
     mágico
    1.79
     kolejny
    1.79
     fría
    1.78
     nasze
    1.78
    Activations Density 0.003%

    No Known Activations