© 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. 11970
    Prev
    Next
    INDEX
    Explanations

    castle and related names

    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
    艄
    -4.50
    跸
    -3.73
    綃
    -3.30
    
    -3.19
    뀨
    -3.19
    慙
    -3.11
    
    -3.11
    ︕
    -3.09
    
    -3.08
    诓
    -3.03
    POSITIVE LOGITS
     give
    3.06
    There
    2.92
     
    2.89
    "
    2.86
     Also
    2.81
    2.81
    :
    2.80
    3
    2.78
    They
    2.78
     Because
    2.70
    Activations Density 0.004%

    No Known Activations