© 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. 1280
    Prev
    Next
    INDEX
    Explanations

    Jay Z or Jay Rock

    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
     it
    -1.98
    n
    -1.73
     cumbersome
    -1.60
    ㎞
    -1.60
    这让
    -1.59
     this
    -1.57
     AssemblyCompany
    -1.54
     seguir
    -1.53
    said
    -1.53
     $=$
    -1.50
    POSITIVE LOGITS
    衚
    2.19
    archiwizowane
    2.02
    闐
    1.98
    乆
    1.98
     剧照
    1.97
    媖
    1.91
    вгений
    1.88
    VERY
    1.88
    푉
    1.87
    ейчас
    1.86
    Activations Density 0.002%

    No Known Activations