© 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. 118346
    Prev
    Next
    INDEX
    Explanations

    code/programming constructs

    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
    zusetzen
    -0.96
     (?,
    -0.89
     ____________
    -0.86
     frumo
    -0.83
     arasındaki
    -0.82
     ï
    -0.81
    
    -0.80
    Important
    -0.80
     неизвест
    -0.79
    tellbar
    -0.79
    POSITIVE LOGITS
     ``
    0.88
    诙
    0.84
     esto
    0.80
     über
    0.80
     escorted
    0.79
     pervasive
    0.78
     At
    0.77
     kesehatan
    0.77
     patho
    0.77
     my
    0.77
    Activations Density 0.020%

    No Known Activations