© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48248
    Prev
    Next
    INDEX
    Explanations

    file pathsdirectories with slashes

    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
     acabado
    -1.64
     erklär
    -1.55
     suelen
    -1.55
     its
    -1.55
    一个是
    -1.51
     приняли
    -1.50
     pesados
    -1.47
     frág
    -1.47
     asesinado
    -1.47
     suele
    -1.45
    POSITIVE LOGITS
     of
    3.42
    
    1.82
     reisen
    1.66
     berge
    1.65
     ideen
    1.63
     artig
    1.63
    although
    1.63
    虽然
    1.62
     Tinggi
    1.55
     invita
    1.55
    Activations Density 0.004%

    No Known Activations