© 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. 110900
    Prev
    Next
    INDEX
    Explanations

    assignments of required modules

    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
     McDonalds
    -0.91
     حا
    -0.86
     nôtre
    -0.85
     fernando
    -0.85
     laura
    -0.84
     Vrbo
    -0.84
     doctr
    -0.84
     démo
    -0.84
     intrigu
    -0.83
     Bute
    -0.83
    POSITIVE LOGITS
     void
    1.02
     perhaps
    1.01
     some
    0.98
     those
    0.97
     氏
    0.94
     Kapelle
    0.94
     Wartawan
    0.94
     something
    0.92
     Thần
    0.90
     this
    0.89
    Activations Density 0.024%

    No Known Activations