© 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. 45592
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and bitwise operations

    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
     bén
    -0.84
    enné
    -0.81
    getDevice
    -0.78
    volle
    -0.77
     directorio
    -0.75
    quill
    -0.75
     Pourquoi
    -0.75
    пта
    -0.75
     certains
    -0.74
    须
    -0.74
    POSITIVE LOGITS
    諷
    0.82
     hưng
    0.71
    回合
    0.70
    足りない
    0.69
     незавер
    0.69
    ("")){
    0.69
    Dependency
    0.69
     Northeastern
    0.68
     Along
    0.68
     Eighty
    0.67
    Activations Density 0.010%

    No Known Activations