© 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. 38151
    Prev
    Next
    INDEX
    Explanations

    game maker, hardware partners, reliable

    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
    ]_{\
    -1.23
     автомобиль
    -1.05
     stát
    -1.05
    yaar
    -1.01
    および
    -0.98
    makta
    -0.96
    Persons
    -0.95
     olej
    -0.95
    ниться
    -0.94
    ఽ
    -0.94
    POSITIVE LOGITS
    REUTERS
    1.14
     Messrs
    1.12
     roughly
    1.11
    peka
    1.09
    wsj
    1.08
     היתה
    1.08
     impri
    1.05
     adviser
    0.98
     jil
    0.98
    isuke
    0.98
    Activations Density 0.190%

    No Known Activations