© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141307
    Prev
    Next
    INDEX
    Explanations

    formal phrases and statements

    np_acts-logits-general · gemini-2.5-flash-lite

    evaluating limitations and safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    takePhotoButton
    0.53
    运作
    0.52
    桑
    0.49
    Portugal
    0.48
    请
    0.48
    默认
    0.47
    ıldı
    0.46
    Bạn
    0.46
    离子
    0.46
     请
    0.46
    POSITIVE LOGITS
     анали
    0.50
     Cherokee
    0.49
     stricken
    0.48
     analyze
    0.46
     божомолу
    0.45
     Mickey
    0.44
     анализа
    0.43
     analisa
    0.42
     Marietta
    0.42
    [,]
    0.41
    Activations Density 0.002%

    No Known Activations