© 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. 34-GEMMASCOPE-RES-131K
    7. 98051
    Prev
    Next
    INDEX
    Explanations

    proper noun phrases

    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_34/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
     mín
    -1.57
     our
    -1.52
    贋
    -1.48
     televiz
    -1.43
     lancar
    -1.39
     bulan
    -1.35
     indiví
    -1.35
     ditem
    -1.33
     sehr
    -1.32
    ॄ
    -1.32
    POSITIVE LOGITS
    one
    1.43
    必要がある
    1.33
     Однако
    1.27
     違い
    1.20
     praktische
    1.20
    たまに
    1.17
     indisputable
    1.17
     следует
    1.16
    no
    1.15
     Этот
    1.15
    Activations Density 0.577%

    No Known Activations