© 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. 98181
    Prev
    Next
    INDEX
    Explanations

    irish 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
     Nevis
    -0.79
     Deepak
    -0.76
     Calvin
    -0.75
    дни
    -0.75
     Samuel
    -0.74
     david
    -0.72
     diploid
    -0.72
     Gideon
    -0.71
    Eben
    -0.71
     elástico
    -0.69
    POSITIVE LOGITS
     Irish
    1.41
    Irish
    1.25
     Connolly
    1.16
     irish
    1.16
    nessy
    1.09
     McCabe
    1.05
    Brendan
    1.02
    anagh
    1.02
    ☘
    1.00
    AHAN
    0.97
    Activations Density 0.074%

    No Known Activations