© 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. 70832
    Prev
    Next
    INDEX
    Explanations

    Penang, CEA, Benton

    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
    蕯
    -2.53
    硖
    -2.52
    ዡ
    -2.34
     gewiß
    -2.30
     gelassen
    -2.28
     burbujas
    -2.28
     bemerkt
    -2.27
    ⸒
    -2.25
     erheblich
    -2.25
     rasch
    -2.25
    POSITIVE LOGITS
    the
    2.86
    }
    2.63
            
    2.63
     suami
    2.52
    ского
    2.44
                
    2.44
    }{
    2.34
    翾
    2.31
    籴
    2.22
      
    2.19
    Activations Density 0.009%

    No Known Activations