© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107223
    Prev
    Next
    INDEX
    Explanations

    Italian surnames

    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
    ډ
    -0.86
    diksi
    -0.81
    éfono
    -0.80
    ergies
    -0.79
     ẩn
    -0.73
    ليل
    -0.71
    兩種
    -0.71
     lido
    -0.70
     lavoratori
    -0.70
     целом
    -0.69
    POSITIVE LOGITS
    悠悠
    0.77
     около
    0.75
     profitieren
    0.73
     fino
    0.72
     comenta
    0.71
     laut
    0.71
     score
    0.71
     worthwhile
    0.71
     câ
    0.70
    ashvili
    0.70
    Activations Density 0.053%

    No Known Activations