© 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. 105236
    Prev
    Next
    INDEX
    Explanations

    past participle form "ed"

    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
    ⮜
    -2.22
     några
    -2.09
    ྵ
    -2.06
    صدار
    -2.05
    踱
    -2.02
    捋
    -1.95
    镔
    -1.89
    せよ
    -1.85
    呖
    -1.84
     blest
    -1.79
    POSITIVE LOGITS
    '
    2.58
    [
    2.08
    乆
    2.06
    ness
    2.03
     penyanyi
    2.02
     ツリー
    1.95
    atser
    1.93
     the
    1.93
    狁
    1.90
    *
    1.84
    Activations Density 0.038%

    No Known Activations