© 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. 59875
    Prev
    Next
    INDEX
    Explanations

    national parks and titles

    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
    __*/
    -0.81
     Globalization
    -0.71
    шити
    -0.71
    🩷
    -0.71
    raquo
    -0.71
    يام
    -0.70
     $\{\
    -0.69
    ardos
    -0.69
    Holstein
    -0.68
     squads
    -0.68
    POSITIVE LOGITS
     national
    3.41
    national
    2.98
     National
    2.75
    National
    2.73
    NATIONAL
    2.39
     parks
    2.34
     NATIONAL
    2.33
     национа
    2.33
     nacional
    2.09
     Parks
    1.87
    Activations Density 0.054%

    No Known Activations