© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83854
    Prev
    Next
    INDEX
    Explanations

    been + past participle

    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
    Negative Logits
     bénéficiaire
    -1.45
    Джерело
    -1.41
    Конечно
    -1.41
     يمكن
    -1.39
    ｢
    -1.38
     coupable
    -1.37
    Их
    -1.34
    Противо
    -1.30
    中身
    -1.30
    もちろん
    -1.30
    POSITIVE LOGITS
    infant
    1.40
     the
    1.34
    organizations
    1.30
    眎
    1.29
    なのですが
    1.29
    لی
    1.29
     LATEST
    1.27
    
    1.27
     összefoglal
    1.27
    bandit
    1.26
    Activations Density 0.072%

    No Known Activations