© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9367
    Prev
    Next
    INDEX
    Explanations

    doesn't

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

    introducing a detailed explanation

    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_40_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
    orthy
    0.42
     Fine
    0.38
    orph
    0.38
    щением
    0.38
     Reebok
    0.38
     فهي
    0.37
    cents
    0.37
    ~~~~~~~~~~~~~~~~
    0.37
    बलेट
    0.36
    omia
    0.36
    POSITIVE LOGITS
       
    0.61
      
    0.59
        
    0.55
            
    0.46
    0.46
    నున్న
    0.45
    0.42
                      
    0.42
                          
    0.42
    Всем
    0.41
    Activations Density 0.047%

    No Known Activations