© 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. 20448
    Prev
    Next
    INDEX
    Explanations

    determiner followed by specific noun

    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
     unveils
    -1.51
    簠
    -1.43
    せば
    -1.41
    矬
    -1.40
    该如何
    -1.39
     kiu
    -1.38
     comprando
    -1.38
     alip
    -1.33
    eronau
    -1.32
    aided
    -1.32
    POSITIVE LOGITS
     even
    1.91
     bahkan
    1.77
     sogar
    1.72
     jopa
    1.45
     new
    1.43
     relatively
    1.34
     etc
    1.31
     of
    1.31
    ちゃんは
    1.31
     not
    1.30
    Activations Density 0.181%

    No Known Activations