© 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. 196675
    Prev
    Next
    INDEX
    Explanations

    iron strap hinges

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

    tech careers and modern tools

    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
     поза
    0.54
     з
    0.53
     помнить
    0.53
     контроль
    0.52
    வற்ற
    0.51
     명
    0.50
     президента
    0.49
    ンの
    0.48
     президент
    0.48
     контро
    0.48
    POSITIVE LOGITS
          
    0.59
            
    0.50
     hardened
    0.48
     Creole
    0.48
    ↵
    0.48
                    
    0.48
                 
    0.47
    家人
    0.47
                  
    0.46
             
    0.44
    Activations Density 0.001%

    No Known Activations