© 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. 99479
    Prev
    Next
    INDEX
    Explanations

    rugby union or league

    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
     Kohn
    -0.82
     partnered
    -0.78
     centered
    -0.78
    delning
    -0.75
    聯絡
    -0.73
     incen
    -0.71
     pinpoint
    -0.70
     Doy
    -0.70
    膵
    -0.70
     금
    -0.69
    POSITIVE LOGITS
     union
    1.09
     Union
    0.96
    union
    0.91
     XV
    0.83
     scrum
    0.82
    Union
    0.81
     Unions
    0.80
    ề
    0.73
     Scrum
    0.73
     snowman
    0.72
    Activations Density 0.026%

    No Known Activations