© 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. 115897
    Prev
    Next
    INDEX
    Explanations

    the name Ross

    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
    Fifteen
    -0.77
    Бележки
    -0.76
     encompassing
    -0.75
     maybe
    -0.75
     begegnen
    -0.74
     Akademie
    -0.74
    啊啊
    -0.73
    榷
    -0.72
    Modifications
    -0.72
     способствует
    -0.71
    POSITIVE LOGITS
    iter
    1.20
    inière
    0.99
    choose
    0.90
    LYN
    0.89
     nacionales
    0.89
    knecht
    0.87
     jouant
    0.87
    etna
    0.87
    Kenzie
    0.87
    печа
    0.87
    Activations Density 0.006%

    No Known Activations