© 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. 34-GEMMASCOPE-RES-131K
    7. 77635
    Prev
    Next
    INDEX
    Explanations

    synthetic regimes

    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
     takeaways
    -0.80
     premises
    -0.80
     ihan
    -0.78
    閣
    -0.76
     takeaway
    -0.75
    RELAND
    -0.75
    Campos
    -0.73
     bitumen
    -0.71
    英國
    -0.71
    Maryland
    -0.69
    POSITIVE LOGITS
     Australian
    1.21
    Australian
    0.97
     Grat
    0.97
    Grat
    0.95
     australiano
    0.89
     australian
    0.81
     Australia
    0.81
     Canberra
    0.80
     Australians
    0.80
     AUSTR
    0.79
    Activations Density 0.029%

    No Known Activations