© 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. 19079
    Prev
    Next
    INDEX
    Explanations

    pound amounts

    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
    鏵
    -3.25
    鋮
    -3.25
    欵
    -3.23
    
    -3.03
    Most
    -2.94
    ꠥ
    -2.88
    。』
    -2.81
     शुर
    -2.81
    Much
    -2.80
    AdvEx
    -2.80
    POSITIVE LOGITS
    崤
    3.14
    .
    3.13
    蹰
    3.00
    <
    2.95
    2
    2.66
     допол
    2.47
    也在
    2.47
    یا
    2.41
    ра
    2.41
     ajoute
    2.38
    Activations Density 0.003%

    No Known Activations