© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101872
    Prev
    Next
    INDEX
    Explanations

    GaN, Gana, Gann, GAMA, Gac, an, ana

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    鶺
    -2.23
    鹚
    -2.13
     Aluno
    -2.13
    𓋼
    -1.97
    秕
    -1.95
     появится
    -1.92
     обеспечивает
    -1.92
    様な
    -1.91
    隳
    -1.90
     participar
    -1.89
    POSITIVE LOGITS
    Ꮠ
    2.06
            
    1.86
              
    1.80
    就在
    1.77
                    
    1.73
                        
    1.70
    为了
    1.70
     для
    1.69
           
    1.68
     美甲
    1.63
    Activations Density 0.001%

    No Known Activations