© 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. 109345
    Prev
    Next
    INDEX
    Explanations

    program code and parameters

    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
    걍
    -0.85
     Rainfall
    -0.81
    ăn
    -0.79
    奈
    -0.77
     wobei
    -0.77
    Haber
    -0.77
     Macca
    -0.76
    queros
    -0.76
     trol
    -0.75
     φω
    -0.75
    POSITIVE LOGITS
    readers
    0.76
     weib
    0.75
     Reader
    0.75
    rmse
    0.73
     defence
    0.72
     reader
    0.71
     påvir
    0.71
    boiling
    0.71
     provider
    0.71
    defence
    0.71
    Activations Density 0.007%

    No Known Activations