© 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. 34-GEMMASCOPE-RES-131K
    7. 83376
    Prev
    Next
    INDEX
    Explanations

    final operations or return

    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_34/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
     chuy
    -1.05
    Ii
    -1.02
    τεύ
    -1.00
    ㅈ
    -0.98
     Новый
    -0.96
     progrès
    -0.94
     bienvenue
    -0.94
     commencer
    -0.93
    fört
    -0.93
     soportes
    -0.91
    POSITIVE LOGITS
     final
    2.22
     last
    1.77
    final
    1.58
     Final
    1.57
    Final
    1.54
    最后
    1.48
     finishing
    1.45
    最後の
    1.37
     último
    1.37
    最後は
    1.35
    Activations Density 0.008%

    No Known Activations