© 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. 10-GEMMASCOPE-RES-131K
    7. 11901
    Prev
    Next
    INDEX
    Explanations

    UCLA webkit

    np_acts-logits-general · gemini-2.5-flash-lite

    references to UCLA (University of California, Los Angeles).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
                
    -2.42
    ization
    -2.41
     terwijl
    -2.16
    脔
    -2.09
    \
    -2.06
    骜
    -2.05
     ausführ
    -1.98
    Ꮉ
    -1.92
    ྜ
    -1.88
    la
    -1.87
    POSITIVE LOGITS
     другие
    2.27
     Einzelnen
    2.11
     Gegensatz
    2.11
     â
    2.08
     andere
    2.08
    ﱠ
    2.03
     renkli
    2.02
     excelente
    2.02
     autre
    1.94
     Allgemeinen
    1.93
    Activations Density 0.003%

    No Known Activations