© 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. 22-GEMMASCOPE-RES-131K
    7. 35809
    Prev
    Next
    INDEX
    Explanations

    progress and contribution

    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_22/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
    Forrás
    -1.63
    あなた
    -1.48
     ملابس
    -1.46
     किताब
    -1.41
    Spesifikasi
    -1.41
     الشاشة
    -1.41
    {?>
    -1.41
     学生
    -1.38
    Dlaczego
    -1.38
    あなたが
    -1.36
    POSITIVE LOGITS
     we
    1.67
     will
    1.55
     it
    1.45
     now
    1.45
     "
    1.38
     our
    1.37
     should
    1.34
    "
    1.29
    ּוֹ
    1.27
     ancak
    1.24
    Activations Density 0.013%

    No Known Activations