© 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. 50389
    Prev
    Next
    INDEX
    Explanations

    Elasticsearch search queries

    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
     Democrat
    -0.75
     Domestic
    -0.72
     domestic
    -0.72
     ni
    -0.71
     bandwidth
    -0.71
     vaccine
    -0.71
    水晶
    -0.69
    oman
    -0.69
     wy
    -0.68
     superfluous
    -0.68
    POSITIVE LOGITS
    Elastic
    0.88
     scrolled
    0.82
    burnt
    0.79
     جنگ
    0.79
    Ela
    0.77
    Routing
    0.76
     くる
    0.76
    loé
    0.75
     hulk
    0.75
    routing
    0.75
    Activations Density 0.020%

    No Known Activations