© 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. 91240
    Prev
    Next
    INDEX
    Explanations

    code snippets and headlines

    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
    androidx
    -1.09
    锃
    -1.04
     androidx
    -1.00
    ய்ய
    -0.98
    DispatchQueue
    -0.94
    SceneManagement
    -0.92
     fön
    -0.88
     mysqli
    -0.87
    XICO
    -0.86
     rése
    -0.85
    POSITIVE LOGITS
     just
    0.99
     so
    0.90
    

    0.85
     xrange
    0.81
     more
    0.78
     lost
    0.78
     especially
    0.77
     â
    0.75
     <
    0.74
     limited
    0.73
    Activations Density 0.003%

    No Known Activations