© 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. 118962
    Prev
    Next
    INDEX
    Explanations

    special characters and non-English words

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

    sequences of special characters and punctuation marks, particularly symbols like ampersands, carets, colons, tildes, and other non-alphanumeric characters.

    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
     that
    -2.03
     facilitates
    -1.72
     helps
    -1.66
     respirar
    -1.66
     may
    -1.64
     condicionado
    -1.61
     because
    -1.59
     atendido
    -1.57
     might
    -1.55
     what
    -1.48
    POSITIVE LOGITS
     dette
    1.68
    both
    1.60
     aussitôt
    1.59
    
    1.59
     февра
    1.57
     Juillet
    1.55
     ۱۵
    1.52
     DELHI
    1.50
     rerum
    1.50
    椟
    1.48
    Activations Density 0.013%

    No Known Activations