© 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. 109231
    Prev
    Next
    INDEX
    Explanations

    European Space Agency

    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
    ického
    -0.81
    ulemon
    -0.76
    합니다
    -0.75
     speł
    -0.75
     dulce
    -0.72
    True
    -0.71
     początku
    -0.71
    茯
    -0.71
    sterling
    -0.70
    ckle
    -0.70
    POSITIVE LOGITS
     ESA
    1.88
    ESA
    1.63
    esa
    1.37
    Esa
    1.04
     Esa
    1.02
    European
    1.01
     европей
    0.93
     Euros
    0.91
     European
    0.90
     european
    0.88
    Activations Density 0.033%

    No Known Activations