© 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. 110772
    Prev
    Next
    INDEX
    Explanations

    Louis and St. Louis

    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
    remain
    -0.78
    rema
    -0.78
    akses
    -0.75
    snap
    -0.72
     Ashok
    -0.71
     amines
    -0.71
     Fillmore
    -0.71
     Mim
    -0.71
    peł
    -0.70
     installations
    -0.70
    POSITIVE LOGITS
     Cardinals
    1.18
    uitton
    0.83
    ('/:
    0.81
     Obispo
    0.80
     something
    0.78
     connus
    0.75
     esistono
    0.75
    blest
    0.73
    ardos
    0.72
    TOXIC
    0.72
    Activations Density 0.020%

    No Known Activations