© 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. 75594
    Prev
    Next
    INDEX
    Explanations

    connecting to database

    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
    totta
    -0.86
    Quran
    -0.81
    ञ
    -0.80
     Gaw
    -0.78
    ตั้ง
    -0.74
    zog
    -0.73
     Caw
    -0.73
     brutal
    -0.71
     red
    -0.71
     Poy
    -0.71
    POSITIVE LOGITS
    ObjectID
    1.01
     Scooby
    0.96
     MongoClient
    0.92
     dbo
    0.92
     Suffolk
    0.90
    {*}
    0.86
    inserted
    0.86
    Inserted
    0.84
     Inserts
    0.81
     fermer
    0.81
    Activations Density 0.009%

    No Known Activations