© 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. 34-GEMMASCOPE-RES-131K
    7. 45485
    Prev
    Next
    INDEX
    Explanations

    WP prefixes

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

    The neuron flags occurrences of the “wp”/“WP” prefix (e.g. in function names, file paths, or acronyms), i.e. WordPress–related tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    {
    -0.81
     AMAZING
    -0.79
     horrid
    -0.79
     all
    -0.79
     solito
    -0.77
    hitting
    -0.77
     kompak
    -0.77
    isShowing
    -0.77
     conne
    -0.76
     .......
    -0.76
    POSITIVE LOGITS
     WP
    0.88
     wp
    0.86
    humanité
    0.83
    ハウ
    0.79
     ком
    0.77
    farin
    0.77
    चाल
    0.76
    mL
    0.76
    总结
    0.76
     inflate
    0.75
    Activations Density 0.013%

    No Known Activations