© 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. 34-GEMMASCOPE-RES-131K
    7. 47978
    Prev
    Next
    INDEX
    Explanations

    Q: or Why

    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_34/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
    摘要
    -0.79
    Supports
    -0.71
    casi
    -0.70
    tiez
    -0.69
     isother
    -0.67
    
    -0.67
    undy
    -0.67
     dormitórios
    -0.66
     芽
    -0.66
    château
    -0.66
    POSITIVE LOGITS
     arac
    0.77
     Pozna
    0.76
     diman
    0.76
     javascript
    0.75
     veck
    0.73
     witnesses
    0.73
    geometry
    0.72
    ナブル
    0.72
     fosfor
    0.72
    nv
    0.72
    Activations Density 0.001%

    No Known Activations