© 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. 58922
    Prev
    Next
    INDEX
    Explanations

    national park systems

    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
     itself
    -1.33
     was
    -1.19
     after
    -1.05
    k
    -0.99
    8
    -0.98
     Issues
    -0.95
     Agencies
    -0.94
    5
    -0.94
     if
    -0.93
     laquelle
    -0.93
    POSITIVE LOGITS
     которые
    2.19
     themselves
    1.87
     חיצוניים
    1.63
     الذين
    1.49
     których
    1.48
     которыми
    1.38
     kurie
    1.26
     lesquels
    1.24
     مختلف
    1.19
     които
    1.19
    Activations Density 0.014%

    No Known Activations