© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40751
    Prev
    Next
    INDEX
    Explanations

    frequency and how often

    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
    チール
    -1.56
     desglose
    -1.51
    瑋
    -1.48
     désir
    -1.43
     contrasting
    -1.41
    yields
    -1.41
     falsche
    -1.41
    汌
    -1.40
    新た
    -1.40
    筈
    -1.39
    POSITIVE LOGITS
     kunna
    1.71
     הם
    1.66
     ambayo
    1.59
     händer
    1.55
    ），
    1.52
    didSet
    1.51
     spelar
    1.50
    、
    1.46
    yyy
    1.46
     bygga
    1.45
    Activations Density 0.065%

    No Known Activations