© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 110
    Prev
    Next
    INDEX
    Explanations

    (c) marker

    np_acts-logits-general · gemini-2.5-flash-lite

    first items or headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ujeme
    0.17
    اً
    0.17
    ন্যার
    0.15
     Payroll
    0.15
    tailwind
    0.14
    सुद्धा
    0.14
    饴
    0.14
     Chihuahua
    0.14
    Warranty
    0.14
    ाइवेट
    0.14
    POSITIVE LOGITS
    		
    0.18
    						
    0.17
    ד
    0.17
    					
    0.16
     코드
    0.15
     використову
    0.15
     определяет
    0.15
     とする
    0.15
     philosopher
    0.15
    			
    0.14
    Activations Density 8.663%

    No Known Activations