© 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. 130367
    Prev
    Next
    INDEX
    Explanations

    strawberry and related words

    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
    是
    -3.70
    就
    -2.63
    一
    -2.56
    We
    -2.50
    需要
    -2.50
    她
    -2.44
    虽然
    -2.42
    任何
    -2.38
    他
    -2.38
    现在
    -2.36
    POSITIVE LOGITS
    玧
    2.73
     marcada
    2.45
    獃
    2.42
     ибо
    2.41
    驀
    2.39
     ilumina
    2.36
    骉
    2.33
    韪
    2.30
    
    2.25
    縠
    2.25
    Activations Density 0.002%

    No Known Activations