© 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. 34-GEMMASCOPE-RES-131K
    4. 45547
    Prev
    Next
    INDEX
    Explanations

    ID, Metro, Wade, /**

    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_34/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
     Guwahati
    -0.93
    貸
    -0.87
    σθ
    -0.84
    lový
    -0.82
    栢
    -0.81
    ьа
    -0.81
     Pembangunan
    -0.80
     Montmartre
    -0.80
    繆
    -0.80
     Spices
    -0.77
    POSITIVE LOGITS
    archar
    0.98
     Texas
    0.90
    Texas
    0.86
    älv
    0.86
     taas
    0.85
    쁘
    0.85
    电子
    0.83
    		
    0.83
     French
    0.81
    				
    0.79
    Activations Density 0.001%

    No Known Activations