© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1650
    Prev
    Next
    INDEX
    Explanations

    Gaz Grill Review

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

    starts of phrases/clauses

    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_262k_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
    ²',
    0.47
     macar
    0.46
     mites
    0.45
    ۗ
    0.44
     misdemeanor
    0.44
     misdemean
    0.44
     peritoneum
    0.43
    BURG
    0.42
     biofilms
    0.42
     transceiver
    0.42
    POSITIVE LOGITS
    ↵
    0.72
            
    0.65
           
    0.62
              
    0.61
    ↵↵
    0.56
       
    0.56
        
    0.56
         
    0.55
               
    0.55
          
    0.55
    Activations Density 0.002%

    No Known Activations