© 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. 119381
    Prev
    Next
    INDEX
    Explanations

    Sardinia and Italy

    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
     agrico
    -0.76
     เจ
    -0.76
     audits
    -0.75
     Schloss
    -0.70
     cứu
    -0.69
    arrivo
    -0.69
     skir
    -0.69
    東西
    -0.68
     erfolgreich
    -0.68
    Jama
    -0.68
    POSITIVE LOGITS
     Sardinia
    1.52
     Cagliari
    1.47
     Sardin
    1.29
     Sardegna
    0.92
     Corsica
    0.88
    Cors
    0.86
    casted
    0.81
    closedir
    0.80
     Nied
    0.79
     Duval
    0.79
    Activations Density 0.023%

    No Known Activations