© 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. 85094
    Prev
    Next
    INDEX
    Explanations

    auxiliary verb + be

    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
     concurrently
    -1.88
    没有什么
    -1.84
    شق
    -1.77
     need
    -1.71
     refurb
    -1.70
     following
    -1.69
    řeba
    -1.64
     вышла
    -1.61
     использование
    -1.59
    ibilidade
    -1.59
    POSITIVE LOGITS
    -:
    1.93
    ۔
    1.91
    栳
    1.85
     the
    1.84
     ordinaires
    1.84
    (“
    1.78
    .»
    1.78
    siempre
    1.76
     dezelve
    1.76
    ING
    1.75
    Activations Density 0.013%

    No Known Activations