© 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. 110959
    Prev
    Next
    INDEX
    Explanations

    oven and baking

    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
    赑
    -1.96
    是怎么回事
    -1.66
    寕
    -1.61
    炻
    -1.60
    ternut
    -1.59
    뿡
    -1.59
    therners
    -1.58
    romeda
    -1.57
    
    -1.56
    𓆸
    -1.55
    POSITIVE LOGITS
    _
    1.70
     same
    1.68
     be
    1.62
     –
    1.56
    ↵
    1.52
    –
    1.52
     =
    1.48
    剮
    1.46
    In
    1.44
     >
    1.41
    Activations Density 0.023%

    No Known Activations