© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99309
    Prev
    Next
    INDEX
    Explanations

    Welsh surnames and names

    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
    iddish
    -0.77
     farol
    -0.76
     planeta
    -0.70
    Zend
    -0.69
    аза
    -0.69
    ğin
    -0.68
    planar
    -0.67
    chit
    -0.67
     discernible
    -0.66
    rzysz
    -0.66
    POSITIVE LOGITS
     Jones
    1.71
     Davies
    1.60
    Jones
    1.52
     Evans
    1.42
     JONES
    1.40
     Williams
    1.35
     jones
    1.34
    Davies
    1.33
    jones
    1.33
     Rhys
    1.27
    Activations Density 0.044%

    No Known Activations