© 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. 724
    Prev
    Next
    INDEX
    Explanations

    prefixes of foreign words 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
    互联网档案馆
    -1.08
     Anforderungen
    -1.02
     berbagai
    -1.02
     sekä
    -1.01
     penggunaan
    -0.97
    捗
    -0.97
     außerdem
    -0.97
     aquellos
    -0.96
     éstos
    -0.96
     Regionen
    -0.96
    POSITIVE LOGITS
     cérami
    1.13
     enchufe
    1.11
    を始め
    1.06
    を行います
    1.06
     Tourisme
    1.05
     dealloc
    1.05
    んだよね
    1.05
    総評
    1.04
     Protobuf
    1.02
     MEGA
    1.00
    Activations Density 0.146%

    No Known Activations