© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 27
    Prev
    Next
    INDEX
    Explanations

    questions about medical treatment

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

    opening brackets, quotation marks, and question marks, particularly at the beginning of dialogue or questions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     but
    -2.11
    .
    -1.78
     our
    -1.72
     we
    -1.60
     these
    -1.58
     all
    -1.49
    たちは
    -1.40
        
    -1.38
          
    -1.32
           
    -1.31
    POSITIVE LOGITS
    //!
    
    1.57
    ="";
    
    1.42
     icône
    1.39
     variété
    1.38
    ⦄
    1.37
     предназна
    1.34
     cimetière
    1.33
    ;}
    
    1.31
    `;
    
    1.30
     結婚
    1.30
    Activations Density 0.015%

    No Known Activations