© 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. 65631
    Prev
    Next
    INDEX
    Explanations

    starts with ar

    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
     моя
    -2.64
    狁
    -2.63
     ſou
    -2.56
    豋
    -2.55
    呖
    -2.53
    圌
    -2.47
     ,‬
    -2.44
    
    -2.44
    狴
    -2.42
    婞
    -2.34
    POSITIVE LOGITS
     This
    2.67
     infamous
    2.61
     frühen
    2.56
     Would
    2.55
     Despite
    2.45
     ar
    2.45
     my
    2.38
     Personally
    2.38
    邂
    2.36
     What
    2.28
    Activations Density 0.027%

    No Known Activations