© 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. 105077
    Prev
    Next
    INDEX
    Explanations

    writable storage, neatly presented

    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
    
    -3.11
    鼉
    -3.03
    
    -2.98
    鱨
    -2.88
    represent
    -2.88
    蟊
    -2.86
    
    -2.83
    鶫
    -2.72
    
    -2.69
    鬭
    -2.64
    POSITIVE LOGITS
     That
    3.92
    та
    3.55
     However
    3.17
     Trying
    3.00
     When
    3.00
     Those
    3.00
     Each
    2.83
     Going
    2.83
     wayward
    2.77
     Following
    2.75
    Activations Density 0.003%

    No Known Activations