© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63384
    Prev
    Next
    INDEX
    Explanations

    regex splitting

    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
    Pane
    -0.81
    ributions
    -0.80
    ෝ
    -0.79
     htons
    -0.77
    ρι
    -0.76
    èvement
    -0.75
    zionamento
    -0.75
    ánea
    -0.75
     strconv
    -0.73
     monitor
    -0.73
    POSITIVE LOGITS
     Regex
    1.30
    Regex
    0.90
    regexp
    0.80
     anoche
    0.72
     Pandemic
    0.72
    Regexp
    0.71
     Bronx
    0.70
    튬
    0.70
     sanguine
    0.69
    zerw
    0.69
    Activations Density 0.014%

    No Known Activations