© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8901
    Prev
    Next
    INDEX
    Explanations

    web development and databases

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

    The neuron fires on generic SEO/disclaimer boilerplate about using the site or the internet to find information or files (e.g. phrases like “easy to find,” “just a search engine,” “internet to find facts,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seaborn
    0.65
    ꔹ
    0.62
     topsail
    0.60
     दै
    0.59
    uluh
    0.57
    βε
    0.57
    घ्र
    0.56
    hita
    0.56
    剡
    0.56
     okul
    0.56
    POSITIVE LOGITS
     interactivity
    0.74
     databases
    0.70
     conceptually
    0.65
     businesses
    0.63
     webpages
    0.63
     interactive
    0.62
     graphically
    0.62
     Content
    0.62
     HTML
    0.61
    interactive
    0.61
    Activations Density 0.100%

    No Known Activations