© 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. 28986
    Prev
    Next
    INDEX
    Explanations

    handling function return statements

    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
            
    -2.03
     berikan
    -1.96
     один
    -1.96
     если
    -1.95
     في
    -1.95
    On
    -1.89
    ৭
    -1.88
     \&
    -1.87
     wurde
    -1.84
    ቨ
    -1.83
    POSITIVE LOGITS
    歺
    2.47
    の商品
    2.42
    逦
    2.39
    の種類
    2.36
     Would
    2.34
    駸
    2.34
     Certificado
    2.31
     Entrega
    2.28
     Preferencias
    2.16
    の紹介
    2.16
    Activations Density 0.015%

    No Known Activations