© 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. 10-GEMMASCOPE-RES-131K
    7. 75070
    Prev
    Next
    INDEX
    Explanations

    has always been

    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_10/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
    婊
    -2.03
    王爷
    -1.93
    渽
    -1.87
    豌
    -1.86
     אתה
    -1.86
    京城
    -1.78
    驸
    -1.78
    焱
    -1.78
    rovnik
    -1.76
    嬷
    -1.76
    POSITIVE LOGITS
    一些
    2.14
    ly
    2.06
    一個
    2.03
    ’
    1.98
     was
    1.87
     виправи
    1.85
    !”
    1.81
    第一个
    1.80
    '
    1.80
    が
    1.77
    Activations Density 0.009%

    No Known Activations