© 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. 34-GEMMASCOPE-RES-131K
    4. 54341
    Prev
    Next
    INDEX
    Explanations

    regex character sets and ranges

    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
    数字
    -1.38
     numerical
    -1.27
     numeric
    -1.23
    isNumber
    -1.16
     numbers
    -1.16
     Numeric
    -1.16
     Numerical
    -1.10
    Numeric
    -1.09
     数字
    -1.09
     números
    -1.06
    POSITIVE LOGITS
    isalpha
    0.93
     מוכ
    0.81
    Jelly
    0.79
    からね
    0.79
    Locke
    0.78
    ("-
    0.76
     Negative
    0.76
     cerebro
    0.74
     negative
    0.73
    大きさ
    0.71
    Activations Density 0.022%

    No Known Activations