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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7226
    Prev
    Next
    INDEX
    Explanations

    peeled ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     кино
    0.52
     ವಸ್ತು
    0.52
    安倍
    0.52
    
    0.50
     दट
    0.50
     graphon
    0.49
     этом
    0.48
     ngờ
    0.48
    মোহনের
    0.48
     істори
    0.48
    POSITIVE LOGITS
    -
    0.67
    ↵
    0.62
    0.59
      
    0.55
     sustenance
    0.50
    o
    0.49
    st
    0.46
        
    0.46
    ↵↵
    0.45
    Tips
    0.44
    Activations Density 0.011%

    No Known Activations