© 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. 28900
    Prev
    Next
    INDEX
    Explanations

    almost weekly updates

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

    relative approach

    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
    ائف
    0.52
     کھانا
    0.49
    記述
    0.48
    拵
    0.47
    疾患
    0.47
    ехать
    0.46
    Vacuum
    0.46
    רא
    0.46
    INN
    0.46
    膣
    0.46
    POSITIVE LOGITS
     reserved
    0.48
     `<=`
    0.47
    ary
    0.47
     sek
    0.46
     touted
    0.46
                  
    0.45
     lst
    0.45
         
    0.44
                    
    0.44
                 
    0.44
    Activations Density 0.000%

    No Known Activations