© 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. 70809
    Prev
    Next
    INDEX
    Explanations

    represents geographic entities

    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
     perpetrators
    -0.93
     courses
    -0.92
    DOCX
    -0.91
    xfa
    -0.90
     construção
    -0.89
    utico
    -0.88
     unserer
    -0.88
     Jeśli
    -0.87
    Caring
    -0.86
     Caring
    -0.84
    POSITIVE LOGITS
     during
    0.98
    ในการ
    0.96
     викона
    0.89
     cualquier
    0.88
    xffff
    0.88
     sacri
    0.87
     when
    0.86
    地點
    0.84
    ಇ
    0.84
     任务
    0.82
    Activations Density 0.090%

    No Known Activations