© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39201
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ed, -zed, or -ied

    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
    шего
    -1.80
    سلام
    -1.63
     other
    -1.59
    趵
    -1.56
    /
    -1.56
     plethora
    -1.56
    ?)
    -1.54
    ܜ
    -1.53
    斃
    -1.53
    咝
    -1.50
    POSITIVE LOGITS
    ING
    1.63
    ໊
    1.63
     tornillo
    1.62
    衚
    1.58
     freut
    1.58
    厹
    1.56
    archiwizowane
    1.55
    ῞
    1.55
     która
    1.54
     procurando
    1.54
    Activations Density 0.131%

    No Known Activations