© 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. 22-GEMMASCOPE-RES-131K
    7. 95738
    Prev
    Next
    INDEX
    Explanations

    both or either

    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_22/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
    SYLLABLE
    -1.02
     sustituir
    -0.91
    别的
    -0.90
    良いです
    -0.89
     November
    -0.87
    ="">
    -0.85
     akin
    -0.85
     December
    -0.85
    QSize
    -0.85
    簠
    -0.84
    POSITIVE LOGITS
     both
    1.52
    both
    1.38
     sowohl
    1.24
     ambos
    1.18
     BOTH
    1.13
     både
    1.11
     cả
    1.04
    どっち
    1.03
     ambas
    1.03
    Both
    1.03
    Activations Density 0.035%

    No Known Activations