© 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. 237635
    Prev
    Next
    INDEX
    Explanations

    Catholic Duke

    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
     mandarin
    0.46
     MAND
    0.46
     Mand
    0.45
     Courthouse
    0.45
    刳
    0.45
    ల్ని
    0.44
     Cruz
    0.43
     धन्यवाद
    0.43
    வனின்
    0.43
    ك
    0.43
    POSITIVE LOGITS
             
    0.49
          
    0.48
     জিৎ
    0.47
         
    0.45
    äter
    0.45
           
    0.44
    étés
    0.44
              
    0.44
    विला
    0.43
               
    0.43
    Activations Density 0.001%

    No Known Activations