© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58838
    Prev
    Next
    INDEX
    Explanations

    smallness or diminutive suffixes

    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
     AQUÍ
    -1.93
     特徴
    -1.84
    ޞ
    -1.83
    锨
    -1.78
     Nedir
    -1.78
    
    -1.77
     панели
    -1.76
     policiales
    -1.72
    搅
    -1.72
    会在
    -1.70
    POSITIVE LOGITS
    vantaged
    2.70
    หรือ
    2.66
     или
    2.38
    蛩
    2.31
     sized
    2.31
    р
    2.28
    ish
    2.23
    !)
    2.08
     oder
    2.05
    啬
    2.05
    Activations Density 0.016%

    No Known Activations