© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32596
    Prev
    Next
    INDEX
    Explanations

    regex matching and substitution

    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
    तु
    -0.81
    loß
    -0.78
    openModal
    -0.75
    телям
    -0.72
    showModal
    -0.72
    ѓ
    -0.71
     Dancer
    -0.71
    人に
    -0.71
     Luzern
    -0.70
     equalled
    -0.70
    POSITIVE LOGITS
     Culture
    0.90
     Regex
    0.87
     culture
    0.83
    culture
    0.80
     Rox
    0.79
    =@
    0.78
    ($"{
    0.76
    Culture
    0.74
     cultures
    0.73
    CULTURE
    0.73
    Activations Density 0.018%

    No Known Activations