© 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. 60456
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    lık
    -0.85
     screwed
    -0.76
     hands
    -0.76
     (
    -0.73
     in
    -0.73
    Holidays
    -0.72
    desired
    -0.72
     fel
    -0.72
     non
    -0.71
    herald
    -0.71
    POSITIVE LOGITS
    <h1>
    1.42
    <h3>
    1.36
    <h2>
    1.13
                         
    0.96
    <h4>
    0.94
                     
    0.94
     cualidades
    0.91
     سلامت
    0.91
                      
    0.88
                          
    0.88
    Activations Density 0.022%

    No Known Activations