© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111339
    Prev
    Next
    INDEX
    Explanations

    programming model declarations

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

    import or dependency declaration statements in code (like `use`, `using`, `require`, `import`, `declare`, `model`, `entry`, and `describe`).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
                
    -2.05
        
    -1.56
     surtido
    -1.53
     
    -1.51
       
    -1.48
     kommt
    -1.48
    已经
    -1.45
            
    -1.41
    日の
    -1.39
     secado
    -1.39
    POSITIVE LOGITS
    ’
    1.69
     from
    1.59
    ,”
    1.59
    盏
    1.56
    ांकि
    1.52
    するための
    1.51
     немає
    1.50
    撹
    1.49
    //};
    1.48
     এক
    1.48
    Activations Density 0.007%

    No Known Activations