© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81333
    Prev
    Next
    INDEX
    Explanations

    lists of names

    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
     skulle
    -0.97
    Mazda
    -0.96
    Peugeot
    -0.94
    があります
    -0.89
     pelaksanaan
    -0.88
    inaudible
    -0.86
    Dieses
    -0.85
     تش
    -0.84
     reorgan
    -0.84
    Jaguar
    -0.81
    POSITIVE LOGITS
     John
    1.81
    John
    1.48
     someone
    1.45
     Peter
    1.41
     Alex
    1.39
     Mary
    1.38
     Joe
    1.38
     john
    1.30
     somebody
    1.30
     Mike
    1.29
    Activations Density 0.068%

    No Known Activations