© 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. 50433
    Prev
    Next
    INDEX
    Explanations

    UI elements like card or panel

    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
     form
    -0.91
     香港
    -0.80
    Attempt
    -0.78
     الات
    -0.78
     unintended
    -0.77
     desta
    -0.76
     जाए
    -0.75
     Atmospheric
    -0.75
     Attempt
    -0.75
     longo
    -0.74
    POSITIVE LOGITS
    modal
    1.26
    ároz
    0.91
    .''
    0.89
    為に
    0.83
    conom
    0.83
    MODAL
    0.81
    スッキリ
    0.81
     modal
    0.77
    τας
    0.75
    鹘
    0.75
    Activations Density 0.011%

    No Known Activations