© 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. 90235
    Prev
    Next
    INDEX
    Explanations

    HTML markdown tags

    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
     in
    -2.41
     at
    -2.27
     on
    -2.05
     just
    -1.87
     not
    -1.84
     for
    -1.83
     three
    -1.80
     with
    -1.79
     as
    -1.77
     one
    -1.77
    POSITIVE LOGITS
    <strong>
    2.80
    <b>
    2.38
    <h1>
    2.20
    <blockquote>
    2.08
                
    1.77
    <em>
    1.68
                   
    1.66
                     
    1.58
                       
    1.58
                      
    1.55
    Activations Density 0.071%

    No Known Activations