© 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. 10-GEMMASCOPE-RES-131K
    7. 12929
    Prev
    Next
    INDEX
    Explanations

    jewelry and jewellers

    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_10/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
    荷物
    -1.20
    方法
    -1.16
    ization
    -1.15
     Becoming
    -1.13
     Applying
    -1.13
     lesión
    -1.10
     quirks
    -1.10
     bestand
    -1.09
    er
    -1.09
     letzten
    -1.09
    POSITIVE LOGITS
     jewellery
    1.59
     jewelry
    1.38
     tallas
    1.29
     that
    1.29
     thee
    1.27
    незон
    1.23
     začet
    1.23
     başladı
    1.22
     those
    1.20
     muualla
    1.20
    Activations Density 0.046%

    No Known Activations