© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7414
    Prev
    Next
    INDEX
    Explanations

    `td::` in code files

    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
     sué
    -1.97
     boneca
    -1.95
    Ꮚ
    -1.84
     universelle
    -1.83
     médic
    -1.82
    
    -1.81
     cuerdas
    -1.81
    𖡼
    -1.80
     spirituelle
    -1.78
     toalha
    -1.77
    POSITIVE LOGITS
    ↵
    2.34
    na
    1.89
      
    1.63
     have
    1.62
     pries
    1.55
     it
    1.50
    で見る
    1.47
    .
    1.44
         
    1.40
     レンタル
    1.39
    Activations Density 0.001%

    No Known Activations