© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8903
    Prev
    Next
    INDEX
    Explanations

    accepted rule, method, or risk

    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
    筇
    -3.13
     知道
    -2.52
     uſed
    -2.39
    
    -2.34
    馓
    -2.31
    价格
    -2.25
     he
    -2.20
     italianos
    -2.16
      
    -2.14
     với
    -2.13
    POSITIVE LOGITS
    姈
    3.02
    结语
    2.67
    ization
    2.39
    ized
    2.39
    er
    2.25
    蒟
    2.23
    翾
    2.22
    媗
    2.20
    罨
    2.19
     事例
    2.16
    Activations Density 0.007%

    No Known Activations