© 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. 87189
    Prev
    Next
    INDEX
    Explanations

    Server Timestamp

    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
     detonation
    -0.83
    鉈
    -0.79
    mysql
    -0.79
    DataSnapshot
    -0.78
     mysql
    -0.75
     鈴木
    -0.72
     AWS
    -0.71
    vely
    -0.71
     Angels
    -0.71
     honest
    -0.70
    POSITIVE LOGITS
     Timestamp
    1.12
     document
    0.90
    document
    0.87
    FieldValue
    0.86
     timestamps
    0.83
     Document
    0.83
    Document
    0.82
     Бор
    0.79
    setField
    0.79
    ombat
    0.79
    Activations Density 0.010%

    No Known Activations