© 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. 10317
    Prev
    Next
    INDEX
    Explanations

    technical and research abstracts

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

    Java-style code tokens including package names, imports, class declarations, and method signatures (particularly related to Minecraft mods and APIs).

    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
    ּוֹ
    -2.36
    nước
    -1.95
     великолеп
    -1.90
     Kto
    -1.86
    ַּ
    -1.77
    וּ
    -1.64
     какъ
    -1.60
     Konkur
    -1.58
     lengu
    -1.57
    ﹗
    -1.56
    POSITIVE LOGITS
     урок
    1.70
     you
    1.53
               
    1.52
    による
    1.52
     vostre
    1.52
                
    1.49
     наиболее
    1.48
                   
    1.48
            
    1.45
     sebagai
    1.42
    Activations Density 0.042%

    No Known Activations