© 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. 12148
    Prev
    Next
    INDEX
    Explanations

    cms and ecommerce platforms

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

    The neuron is marking tokens by how far into a block they are—i.e. it fires strongest right at the end of a text segment.

    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
    textnormal
    -0.81
    inbox
    -0.78
     Inbox
    -0.74
    kara
    -0.73
    peration
    -0.73
    *&
    -0.72
     Chid
    -0.72
    guero
    -0.71
    pran
    -0.71
     służ
    -0.71
    POSITIVE LOGITS
     Shopify
    1.67
     WordPress
    1.63
     Magento
    1.63
     Drupal
    1.48
     WooCommerce
    1.43
     Salesforce
    1.38
     WP
    1.30
     Squares
    1.25
    wp
    1.23
     Wordpress
    1.22
    Activations Density 0.224%

    No Known Activations